# Inside The Machine

> Agent-first directory of 242 local-AI tools, models and repos (runtimes, agents, memory, RAG, routing, MCP, UIs, voice, image/video, fine-tuning, quantization, evals, scaffolds, observability, hardware utilities). 13 "runbook" listings have install/verify/rollback checked against official docs; the rest are "catalog" entries with verified metadata and unverified, README-extracted install commands. Gap Scores are pending test on Mac Studio.

Append .md or .json to any /setups/<slug> URL, or send Accept: text/markdown.

## Start here

- [Zero to working local AI](https://insidethemachine.ai/start.md): 5-step runbook + AGENTS.md/SOUL.md + lean-context guide. JSON: https://insidethemachine.ai/start.json
- [Models vs memory](https://insidethemachine.ai/models.md): which open models fit which RAM tier. JSON: https://insidethemachine.ai/models.json (124 text models; plus speech.json and images.json)
- [Machines](https://insidethemachine.ai/machines.md): hardware guide. JSON: https://insidethemachine.ai/machines.json

## Best picks (answers with dated data)

- [Best local LLM by memory](https://insidethemachine.ai/best.md): one table, 8 to 512 GB: models that fit, best model, best coding model
- [Best local LLM for 8 GB RAM or VRAM](https://insidethemachine.ai/best/local-llm-for-8gb-ram.md): top picks, coding/agent/vision pick, machines with 8 GB
- [Best local LLM for 16 GB RAM or VRAM](https://insidethemachine.ai/best/local-llm-for-16gb-ram.md): top picks, coding/agent/vision pick, machines with 16 GB
- [Best local LLM for 24 GB RAM or VRAM](https://insidethemachine.ai/best/local-llm-for-24gb-ram.md): top picks, coding/agent/vision pick, machines with 24 GB
- [Best local LLM for 32 GB RAM or VRAM](https://insidethemachine.ai/best/local-llm-for-32gb-ram.md): top picks, coding/agent/vision pick, machines with 32 GB
- [Best local LLM for 48 GB RAM or VRAM](https://insidethemachine.ai/best/local-llm-for-48gb-ram.md): top picks, coding/agent/vision pick, machines with 48 GB
- [Best local LLM for 64 GB RAM or VRAM](https://insidethemachine.ai/best/local-llm-for-64gb-ram.md): top picks, coding/agent/vision pick, machines with 64 GB
- [Best local LLM for 96 GB RAM or VRAM](https://insidethemachine.ai/best/local-llm-for-96gb-ram.md): top picks, coding/agent/vision pick, machines with 96 GB
- [Best local LLM for 128 GB RAM or VRAM](https://insidethemachine.ai/best/local-llm-for-128gb-ram.md): top picks, coding/agent/vision pick, machines with 128 GB
- [Best local LLM for 192 GB RAM or VRAM](https://insidethemachine.ai/best/local-llm-for-192gb-ram.md): top picks, coding/agent/vision pick, machines with 192 GB
- [Best local LLM for 256 GB RAM or VRAM](https://insidethemachine.ai/best/local-llm-for-256gb-ram.md): top picks, coding/agent/vision pick, machines with 256 GB
- [Best local LLM for 512 GB RAM or VRAM](https://insidethemachine.ai/best/local-llm-for-512gb-ram.md): top picks, coding/agent/vision pick, machines with 512 GB
- [Best local coding model](https://insidethemachine.ai/best/local-coding-model.md): per memory size, Terminal-Bench, coding apps
- [Best local model for agents](https://insidethemachine.ai/best/local-model-for-agents.md): OpenClaw, Hermes Agent and more
- [Best local LLM for Mac](https://insidethemachine.ai/best/local-llm-for-mac.md) · [NVIDIA GPU](https://insidethemachine.ai/best/local-llm-for-nvidia-gpu.md) · [mini PC](https://insidethemachine.ai/best/local-llm-for-mini-pc.md)
- [Compare apps](https://insidethemachine.ai/compare.md): [Ollama vs LM Studio](https://insidethemachine.ai/compare/ollama-vs-lm-studio.md) · [Ollama vs llama.cpp](https://insidethemachine.ai/compare/ollama-vs-llama-cpp.md) · [LM Studio vs llama.cpp](https://insidethemachine.ai/compare/lm-studio-vs-llama-cpp.md) · [MLX LM vs Ollama](https://insidethemachine.ai/compare/mlx-lm-vs-ollama.md) · [Open WebUI vs LM Studio](https://insidethemachine.ai/compare/open-webui-vs-lm-studio.md)
- Alternatives: [Ollama](https://insidethemachine.ai/alternatives/ollama.md) · [MLX LM](https://insidethemachine.ai/alternatives/mlx-lm.md) · [LM Studio](https://insidethemachine.ai/alternatives/lm-studio.md) · [llama.cpp](https://insidethemachine.ai/alternatives/llama-cpp.md) · [Aider](https://insidethemachine.ai/alternatives/aider.md) · [Hermes Agent](https://insidethemachine.ai/alternatives/hermes-agent.md) · [LiteLLM](https://insidethemachine.ai/alternatives/litellm.md) · [Mem0](https://insidethemachine.ai/alternatives/mem0.md) · [Docling](https://insidethemachine.ai/alternatives/docling.md) · [Open WebUI](https://insidethemachine.ai/alternatives/open-webui.md) · [whisper.cpp](https://insidethemachine.ai/alternatives/whisper-cpp.md)
- Machines (one page each): [MacBook Air 13"/15" (M5)](https://insidethemachine.ai/machines/macbook-air-m5.md) · [MacBook Pro 14" (M5)](https://insidethemachine.ai/machines/macbook-pro-14-m5.md) · [MacBook Pro 14"/16" (M5 Pro)](https://insidethemachine.ai/machines/macbook-pro-m5-pro.md) · [MacBook Pro 14"/16" (M5 Max)](https://insidethemachine.ai/machines/macbook-pro-m5-max.md) · [Mac mini (M6)](https://insidethemachine.ai/machines/mac-mini-m6.md) · [Mac mini (M5 Pro)](https://insidethemachine.ai/machines/mac-mini-m5-pro.md) · [Mac Studio (M5 Max)](https://insidethemachine.ai/machines/mac-studio-m5-max.md) · [Mac Studio (M5 Ultra)](https://insidethemachine.ai/machines/mac-studio-m5-ultra.md) · [GeForce RTX 5090](https://insidethemachine.ai/machines/rtx-5090.md) · [GeForce RTX 5080](https://insidethemachine.ai/machines/rtx-5080.md) · [GeForce RTX 5070 Ti](https://insidethemachine.ai/machines/rtx-5070-ti.md) · [GeForce RTX 5070](https://insidethemachine.ai/machines/rtx-5070.md) · [GeForce RTX 5060 Ti 16GB](https://insidethemachine.ai/machines/rtx-5060-ti-16gb.md) · [GeForce RTX 5060](https://insidethemachine.ai/machines/rtx-5060.md) · [GeForce RTX 4090](https://insidethemachine.ai/machines/rtx-4090.md) · [GeForce RTX 4080 Super](https://insidethemachine.ai/machines/rtx-4080-super.md) · [GeForce RTX 4070 Ti Super](https://insidethemachine.ai/machines/rtx-4070-ti-super.md) · [GeForce RTX 4060 Ti 16GB](https://insidethemachine.ai/machines/rtx-4060-ti-16gb.md) · [GeForce RTX 3090 (used)](https://insidethemachine.ai/machines/rtx-3090.md) · [GeForce RTX 3090 Ti](https://insidethemachine.ai/machines/rtx-3090-ti.md) · [GeForce RTX 3060 12GB (used)](https://insidethemachine.ai/machines/rtx-3060-12gb.md) · [RTX PRO 6000 Blackwell Workstation (96GB)](https://insidethemachine.ai/machines/rtx-pro-6000-blackwell.md) · [RTX PRO 6000 Blackwell Max-Q (96GB)](https://insidethemachine.ai/machines/rtx-pro-6000-blackwell-maxq.md) · [RTX PRO 5000 Blackwell 72GB](https://insidethemachine.ai/machines/rtx-pro-5000-blackwell-72gb.md) · [RTX PRO 4500 Blackwell 32GB](https://insidethemachine.ai/machines/rtx-pro-4500-blackwell.md) · [RTX PRO 4000 Blackwell 24GB](https://insidethemachine.ai/machines/rtx-pro-4000-blackwell.md) · [NVIDIA DGX Spark (128GB)](https://insidethemachine.ai/machines/dgx-spark-128gb.md) · [DGX Spark 64GB (partner GB10 systems)](https://insidethemachine.ai/machines/dgx-spark-64gb.md) · [NVIDIA Jetson AGX Thor Developer Kit](https://insidethemachine.ai/machines/jetson-agx-thor.md) · [NVIDIA Jetson Orin Nano Super Developer Kit](https://insidethemachine.ai/machines/jetson-orin-nano-super.md) · [Framework Desktop (Ryzen AI Max+ 395)](https://insidethemachine.ai/machines/framework-desktop-395.md) · [GMKtec EVO-X2 (Ryzen AI Max+ 395)](https://insidethemachine.ai/machines/gmktec-evo-x2.md) · [Minisforum MS-S1 MAX (Ryzen AI Max+ 395)](https://insidethemachine.ai/machines/minisforum-ms-s1-max.md) · [Bosgame M5 (Ryzen AI Max+ 395)](https://insidethemachine.ai/machines/bosgame-m5.md) · [Beelink GTR9 Pro (Ryzen AI Max+ 395)](https://insidethemachine.ai/machines/beelink-gtr9-pro.md) · [GMKtec EVO-X5 Pro (Ryzen AI Max+ PRO 495 "Gorgon Halo")](https://insidethemachine.ai/machines/gmktec-evo-x5-pro.md) · [Radeon RX 7900 XTX](https://insidethemachine.ai/machines/radeon-rx-7900-xtx.md) · [Radeon RX 9070 XT](https://insidethemachine.ai/machines/radeon-rx-9070-xt.md) · [Radeon AI PRO R9700 (32GB)](https://insidethemachine.ai/machines/radeon-ai-pro-r9700.md) · [Intel Arc B580](https://insidethemachine.ai/machines/intel-arc-b580.md) · [Intel Arc Pro B60 (24GB)](https://insidethemachine.ai/machines/intel-arc-pro-b60.md) · [Intel Arc Pro B70 (32GB)](https://insidethemachine.ai/machines/intel-arc-pro-b70.md) · [Raspberry Pi 5 (16GB), CPU only](https://insidethemachine.ai/machines/raspberry-pi-5-16gb.md) · [Tesla P40 24GB (used)](https://insidethemachine.ai/machines/tesla-p40.md) · [AMD Instinct MI50 32GB (used)](https://insidethemachine.ai/machines/instinct-mi50-32gb.md) · [Tesla V100 PCIe 32GB (used)](https://insidethemachine.ai/machines/tesla-v100-32gb.md) · [Minisforum MS-S1 MAX-P495 (Ryzen AI Max+ PRO 495 "Gorgon Halo")](https://insidethemachine.ai/machines/minisforum-ms-s1-max-p495.md) · [Gigabyte W775-V10-L01 (DGX Station GB300)](https://insidethemachine.ai/machines/gigabyte-w775-v10-l01.md) · [ASUS ProArt GR1X (NVIDIA RTX Spark)](https://insidethemachine.ai/machines/asus-proart-gr1x.md) · [iBUYPOWER Pro AMD AI Halo Mini PC (Ryzen AI Max+ PRO 495)](https://insidethemachine.ai/machines/ibuypower-pro-amd-ai-halo.md) · [Microsoft Surface RTX Spark Dev Box (128GB)](https://insidethemachine.ai/machines/surface-rtx-spark-dev-box.md) · [AMD Ryzen AI Halo Developer Platform (Ryzen AI Max+ PRO 495, 192GB)](https://insidethemachine.ai/machines/amd-ryzen-ai-halo-495.md) · [Sipeed MaixStation](https://insidethemachine.ai/machines/sipeed-maixstation.md)

## Your machine, one-command installs, what changed

- [Scan my machine](https://insidethemachine.ai/scan.sh): read-only; prints a https://insidethemachine.ai/my?... link. Windows: https://insidethemachine.ai/scan.ps1. Report for agents: https://insidethemachine.ai/my.json?ram=<GB>&os=<mac|linux|win>&chip=<slug>&gpu=<slug>&vram=<GB> (also /my.md)
- [One-command installs](https://insidethemachine.ai/install.md): 19 scripts with install, verify, rollback and an honest run status. JSON: https://insidethemachine.ai/install.json
- [Install: A private ChatGPT](https://insidethemachine.ai/install/chat.md) [ran]: `curl -fsSL https://insidethemachine.ai/install/chat.sh | bash`
- [Install: A coding helper](https://insidethemachine.ai/install/code.md) [partly-ran]: `curl -fsSL https://insidethemachine.ai/install/code.sh | bash`
- [Install: Chat with your files](https://insidethemachine.ai/install/docs.md) [partly-ran]: `curl -fsSL https://insidethemachine.ai/install/docs.sh | bash`
- [Install: Speech to text](https://insidethemachine.ai/install/voice.md) [ran]: `curl -fsSL https://insidethemachine.ai/install/voice.sh | bash`
- [Install: Make images](https://insidethemachine.ai/install/images.md) [not-run]: `curl -fsSL https://insidethemachine.ai/install/images.sh | bash`
- [Install: An agent that does tasks](https://insidethemachine.ai/install/agent.md) [docs-checked]: `curl -fsSL https://insidethemachine.ai/install/agent.sh | bash`
- [Install: MLX LM](https://insidethemachine.ai/install/mlx-lm.md) [docs-checked]: `curl -fsSL https://insidethemachine.ai/install/mlx-lm.sh | bash`
- [Install: Ollama](https://insidethemachine.ai/install/ollama.md) [docs-checked]: `curl -fsSL https://insidethemachine.ai/install/ollama.sh | bash`
- [Install: llama.cpp](https://insidethemachine.ai/install/llama-cpp.md) [docs-checked]: `curl -fsSL https://insidethemachine.ai/install/llama-cpp.sh | bash`
- [Install: LM Studio](https://insidethemachine.ai/install/lm-studio.md) [docs-checked]: `curl -fsSL https://insidethemachine.ai/install/lm-studio.sh | bash`
- [Install: Open WebUI](https://insidethemachine.ai/install/open-webui.md) [docs-checked]: `curl -fsSL https://insidethemachine.ai/install/open-webui.sh | bash`
- [Install: LiteLLM](https://insidethemachine.ai/install/litellm.md) [docs-checked]: `curl -fsSL https://insidethemachine.ai/install/litellm.sh | bash`
- [Install: Aider](https://insidethemachine.ai/install/aider.md) [docs-checked]: `curl -fsSL https://insidethemachine.ai/install/aider.sh | bash`
- [Install: Hermes Agent](https://insidethemachine.ai/install/hermes-agent.md) [docs-checked]: `curl -fsSL https://insidethemachine.ai/install/hermes-agent.sh | bash`
- [Install: Mem0](https://insidethemachine.ai/install/mem0.md) [docs-checked]: `curl -fsSL https://insidethemachine.ai/install/mem0.sh | bash`
- [Install: MCP Servers (official)](https://insidethemachine.ai/install/mcp-servers.md) [docs-checked]: `curl -fsSL https://insidethemachine.ai/install/mcp-servers.sh | bash`
- [Install: whisper.cpp](https://insidethemachine.ai/install/whisper-cpp.md) [docs-checked]: `curl -fsSL https://insidethemachine.ai/install/whisper-cpp.sh | bash`
- [Install: Docling](https://insidethemachine.ai/install/docling.md) [docs-checked]: `curl -fsSL https://insidethemachine.ai/install/docling.sh | bash`
- [Install: AGENTS.md](https://insidethemachine.ai/install/agents-md.md) [docs-checked]: `curl -fsSL https://insidethemachine.ai/install/agents-md.sh | bash`
- [What changed](https://insidethemachine.ai/changes.md): dated new models (with the memory they need), tools, machines, and what broke. JSON: https://insidethemachine.ai/changes.json · RSS: https://insidethemachine.ai/changes.xml

## Pages (every page also answers Accept: text/markdown)

- [Start here: local AI in plain words](https://insidethemachine.ai/start-here.md): primer + recipe list + the full runbook. JSON: https://insidethemachine.ai/start-here.json
- [Recipes](https://insidethemachine.ai/do.md): 6 goals with memory needs. JSON: https://insidethemachine.ai/do.json
- [Recipe: A private ChatGPT](https://insidethemachine.ai/do/chat.md): steps, model per memory size, rollback, fixes. JSON: https://insidethemachine.ai/do/chat.json
- [Recipe: A coding helper](https://insidethemachine.ai/do/code.md): steps, model per memory size, rollback, fixes. JSON: https://insidethemachine.ai/do/code.json
- [Recipe: Chat with your files](https://insidethemachine.ai/do/docs.md): steps, model per memory size, rollback, fixes. JSON: https://insidethemachine.ai/do/docs.json
- [Recipe: Speech to text](https://insidethemachine.ai/do/voice.md): steps, model per memory size, rollback, fixes. JSON: https://insidethemachine.ai/do/voice.json
- [Recipe: Make images](https://insidethemachine.ai/do/images.md): steps, model per memory size, rollback, fixes. JSON: https://insidethemachine.ai/do/images.json
- [Recipe: An agent that does tasks](https://insidethemachine.ai/do/agent.md): steps, model per memory size, rollback, fixes. JSON: https://insidethemachine.ai/do/agent.json
- [Harnesses](https://insidethemachine.ai/harnesses.md): which app for which job, Claude Code vs Codex with local models. JSON: https://insidethemachine.ai/harnesses.json
- [Advanced: an agent that improves itself](https://insidethemachine.ai/guides/agent.md): same as start.md. JSON: https://insidethemachine.ai/guides/agent.json
- [Gap Score](https://insidethemachine.ai/gap-score.md): methodology, no scores yet. JSON: https://insidethemachine.ai/gap-score.json

## Core

- [Catalog JSON](https://insidethemachine.ai/api/index.json): every listing with links
- [Listing JSON Schema](https://insidethemachine.ai/schema/listing.schema.json)
- [Full text](https://insidethemachine.ai/llms-full.txt)
- [Dropped / archived items](https://insidethemachine.ai/api/dropped.json)
- [About / Gap Score methodology](https://insidethemachine.ai/about.md)

## Runtimes & inference

- [Ollama](https://insidethemachine.ai/setups/ollama.md): One command to download and run a model. [runbook]
- [SGLang](https://insidethemachine.ai/setups/sglang.md): High-throughput serving for LLMs and VLMs.
- [MLX](https://insidethemachine.ai/setups/mlx.md): Apple's array framework for Apple silicon.
- [llamafile](https://insidethemachine.ai/setups/llamafile.md): Package a model and runtime into one executable.
- [MLC LLM](https://insidethemachine.ai/setups/mlc-llm.md): Compile and run LLMs on any device.
- [KoboldCpp](https://insidethemachine.ai/setups/koboldcpp.md): One-file GGUF runner with a built-in UI.
- [MLX Examples](https://insidethemachine.ai/setups/mlx-examples.md): Official MLX example models and scripts.
- [MLX LM](https://insidethemachine.ai/setups/mlx-lm.md): Runs LLMs natively on Apple silicon. [runbook]
- [llama-swap](https://insidethemachine.ai/setups/llama-swap.md): Hot-swaps models behind one OpenAI-style endpoint.
- [MLX-VLM](https://insidethemachine.ai/setups/mlx-vlm.md): Vision-language models on MLX.
- [LM Studio](https://insidethemachine.ai/setups/lm-studio.md): A desktop app for local models. [runbook]
- [RamaLama](https://insidethemachine.ai/setups/ramalama.md): Serve models from any source in containers.
- [vLLM Metal](https://insidethemachine.ai/setups/vllm-metal.md): vLLM plugin for Apple Silicon.
- [MLX OpenAI Server](https://insidethemachine.ai/setups/mlx-openai-server.md): OpenAI-compatible API server for MLX models.
- [ML Drift](https://insidethemachine.ai/setups/ml-drift.md): Google's GPU inference engine for edge devices.
- [llama.cpp](https://insidethemachine.ai/setups/llama-cpp.md): The engine behind most local AI. [runbook]
- [vLLM](https://insidethemachine.ai/setups/vllm.md): High-throughput LLM serving engine.

## Model hubs

- [Transformers](https://insidethemachine.ai/setups/transformers.md): The reference library for open model weights.
- [Unsloth notebooks](https://insidethemachine.ai/setups/unsloth-notebooks.md): 250+ ready fine-tuning notebooks.
- [Hugging Face Hub](https://insidethemachine.ai/setups/hugging-face-hub.md): The main hub for open model weights.
- [Ollama Library](https://insidethemachine.ai/setups/ollama-library.md): Ready-to-pull models for Ollama.
- [LM Studio model catalog](https://insidethemachine.ai/setups/lm-studio-models.md): Curated models you can load in LM Studio.
- [mlx-community (Hugging Face)](https://insidethemachine.ai/setups/mlx-community.md): Community MLX conversions of popular models.
- [Unsloth (Hugging Face)](https://insidethemachine.ai/setups/unsloth-models.md): Unsloth GGUF and fine-tune-ready model uploads.
- [lmstudio-community (Hugging Face)](https://insidethemachine.ai/setups/lmstudio-community.md): LM Studio's community GGUF/MLX uploads.
- [Kaggle Models](https://insidethemachine.ai/setups/kaggle-models.md): Google-run model hub with downloadable weights.

## Models from the channel

- [Qwen-Image-2.1-Turbo](https://insidethemachine.ai/setups/qwen-image-2-1-turbo.md): 7B image model that paints and edits in 8 steps.
- [Mellum2.1 12B-A2.5B](https://insidethemachine.ai/setups/mellum-2-1.md): JetBrains coding model, 12B with 2.5B active.
- [EmbeddingGemma 2](https://insidethemachine.ai/setups/embeddinggemma-2.md): 740M on-device embedding model for search.
- [Kolibri-1](https://insidethemachine.ai/setups/kolibri-1.md): Open German/English MoE model (about 78 GB of memory, per the video).
- [AstaBrief 8B](https://insidethemachine.ai/setups/astabrief-8b.md): Small Ai2 model that writes cited reports.
- [Clef](https://insidethemachine.ai/setups/cloudflare-clef.md): Cloudflare's small open decision models (Clef, Clef-flash).

## Coding agents

- [OpenCode](https://insidethemachine.ai/setups/opencode.md): Open-source coding agent for your terminal.
- [Pi (pi-mono)](https://insidethemachine.ai/setups/pi-pi-mono.md): Small agent toolkit: LLM API, agent loop and coding CLI.
- [Goose](https://insidethemachine.ai/setups/goose.md): Extensible open-source agent that runs code and tools.
- [Aider](https://insidethemachine.ai/setups/aider.md): A coding agent in your terminal. [runbook]
- [mini-SWE-agent](https://insidethemachine.ai/setups/mini-swe-agent.md): A 100-line agent that fixes GitHub issues.
- [Claude Code](https://insidethemachine.ai/setups/claude-code.md): Anthropic's terminal coding agent (cloud model).
- [Gemini CLI](https://insidethemachine.ai/setups/gemini-cli.md): Google's open-source terminal agent for Gemini.
- [OpenHands](https://insidethemachine.ai/setups/openhands.md): Open platform for autonomous software agents.
- [Cline](https://insidethemachine.ai/setups/cline.md): Coding agent as a VS Code extension, CLI or SDK.
- [Continue](https://insidethemachine.ai/setups/continue.md): Open-source coding agent for IDEs and CI.
- [Tabby](https://insidethemachine.ai/setups/tabby.md): Self-hosted code completion and chat server.
- [Crush](https://insidethemachine.ai/setups/crush.md): Polished terminal coding agent from Charm.
- [Qwen Code](https://insidethemachine.ai/setups/qwen-code.md): Qwen's open-source terminal coding agent.
- [Kilo Code](https://insidethemachine.ai/setups/kilo-code.md): All-in-one agentic coding extension and CLI.
- [Codex CLI](https://insidethemachine.ai/setups/codex-cli.md): OpenAI's lightweight terminal coding agent.
- [GitHub Copilot CLI](https://insidethemachine.ai/setups/copilot-cli.md): GitHub's terminal coding agent; can use Ollama models.

## General & personal agents

- [OpenClaw](https://insidethemachine.ai/setups/openclaw.md): Personal agent that runs on your machine and chats anywhere.
- [Hermes Agent](https://insidethemachine.ai/setups/hermes-agent.md): A personal agent that learns skills and remembers you. [runbook]
- [AutoGPT](https://insidethemachine.ai/setups/autogpt.md): Platform for building autonomous agents.
- [Browser Use](https://insidethemachine.ai/setups/browser-use.md): Let an AI agent drive a web browser.
- [DeerFlow](https://insidethemachine.ai/setups/deerflow.md): Long-running research and coding super-agent.
- [Open Interpreter](https://insidethemachine.ai/setups/open-interpreter.md): Agent that runs code on your computer, for open models.
- [OpenManus](https://insidethemachine.ai/setups/openmanus.md): Open-source general agent (Manus-style).
- [nanobot](https://insidethemachine.ai/setups/nanobot.md): Ultra-light self-hosted personal agent.
- [UI-TARS Desktop](https://insidethemachine.ai/setups/ui-tars-desktop.md): Multimodal agent that operates your desktop.
- [Khoj](https://insidethemachine.ai/setups/khoj.md): Self-hostable AI second brain over your docs and the web.
- [Perplexica](https://insidethemachine.ai/setups/perplexica.md): Open answering engine (formerly Perplexica).
- [NanoClaw](https://insidethemachine.ai/setups/nanoclaw.md): Lightweight, container-sandboxed OpenClaw alternative.
- [GPT Researcher](https://insidethemachine.ai/setups/gpt-researcher.md): Agent that writes deep research reports.
- [Cua](https://insidethemachine.ai/setups/cua.md): Open-source computer-use drivers and sandboxes.
- [LM Studio Bionic](https://insidethemachine.ai/setups/lm-studio-bionic.md): LM Studio's agent that can run beside the app.

## Agent frameworks

- [LiteLLM](https://insidethemachine.ai/setups/litellm.md): One API in front of every model, local or cloud. [runbook]
- [AutoGen](https://insidethemachine.ai/setups/autogen.md): Microsoft's multi-agent programming framework.
- [CrewAI](https://insidethemachine.ai/setups/crewai.md): Role-based multi-agent framework.
- [LangGraph](https://insidethemachine.ai/setups/langgraph.md): Build stateful, resilient agent graphs.
- [Agno](https://insidethemachine.ai/setups/agno.md): Build and run agent systems in Python.
- [DSPy](https://insidethemachine.ai/setups/dspy.md): Program LLMs instead of hand-writing prompts.
- [OpenAI Agents SDK](https://insidethemachine.ai/setups/openai-agents-sdk.md): OpenAI's lightweight multi-agent SDK.
- [smolagents](https://insidethemachine.ai/setups/smolagents.md): Tiny library for agents that think in code.
- [Mastra](https://insidethemachine.ai/setups/mastra.md): TypeScript framework for agents and workflows.
- [Vercel AI SDK](https://insidethemachine.ai/setups/vercel-ai-sdk.md): TypeScript toolkit for AI apps and agents.
- [Haystack](https://insidethemachine.ai/setups/haystack.md): Orchestration framework for RAG and agents.
- [Letta](https://insidethemachine.ai/setups/letta.md): Stateful agents with long-term memory (ex-MemGPT).
- [Google ADK](https://insidethemachine.ai/setups/google-adk.md): Google's code-first agent development kit.
- [Pydantic AI](https://insidethemachine.ai/setups/pydantic-ai.md): Typed Python agent framework.

## Memory

- [Mem0](https://insidethemachine.ai/setups/mem0.md): Long-term memory for your agent. [runbook]
- [claude-mem](https://insidethemachine.ai/setups/claude-mem.md): Captures agent sessions and replays context later.
- [Cognee](https://insidethemachine.ai/setups/cognee.md): Knowledge-graph memory for agents.
- [Graphiti](https://insidethemachine.ai/setups/graphiti.md): Real-time temporal knowledge graphs for agents.
- [Supermemory](https://insidethemachine.ai/setups/supermemory.md): Fast memory engine and app, can run locally.
- [MemOS](https://insidethemachine.ai/setups/memos.md): Memory operating system for LLM agents.
- [Honcho](https://insidethemachine.ai/setups/honcho.md): Memory library that models users across sessions.
- [Basic Memory](https://insidethemachine.ai/setups/basic-memory.md): Markdown-file memory your agent reads and writes.
- [Memobase](https://insidethemachine.ai/setups/memobase.md): User-profile memory for chat apps.
- [memsearch](https://insidethemachine.ai/setups/memsearch.md): Semantic search over agent memory files.
- [MCP Memory Service](https://insidethemachine.ai/setups/mcp-memory-service.md): Persistent memory exposed as an MCP server.

## RAG & document parsing

- [Docling](https://insidethemachine.ai/setups/docling.md): Turns documents into clean text for AI. [runbook]
- [Marker](https://insidethemachine.ai/setups/marker.md): Fast, accurate PDF-to-markdown converter.
- [LightRAG](https://insidethemachine.ai/setups/lightrag.md): Simple, fast graph-based RAG.
- [Qdrant](https://insidethemachine.ai/setups/qdrant.md): High-performance vector database.
- [Chroma](https://insidethemachine.ai/setups/chroma.md): Open-source embedding database.
- [pgvector](https://insidethemachine.ai/setups/pgvector.md): Vector search inside Postgres.
- [LanceDB](https://insidethemachine.ai/setups/lancedb.md): Embedded multimodal vector database.
- [sqlite-vec](https://insidethemachine.ai/setups/sqlite-vec.md): Vector search as a tiny SQLite extension.
- [MarkItDown](https://insidethemachine.ai/setups/markitdown.md): Convert files and Office docs to markdown.
- [RAGFlow](https://insidethemachine.ai/setups/ragflow.md): Deep-document RAG engine with a UI.
- [PaddleOCR](https://insidethemachine.ai/setups/paddleocr.md): OCR and document parsing toolkit.
- [MinerU](https://insidethemachine.ai/setups/mineru.md): Converts complex PDFs to markdown or JSON.
- [AnythingLLM](https://insidethemachine.ai/setups/anythingllm.md): All-in-one desktop app for chat with your docs.
- [Meilisearch](https://insidethemachine.ai/setups/meilisearch.md): Fast search engine with hybrid vector search.

## Routing & gateways

- [Strands Decider](https://insidethemachine.ai/setups/strands-decider.md): Small decision model that routes agent choices.
- [New API](https://insidethemachine.ai/setups/new-api.md): Unified gateway that converts many LLM APIs.
- [One API](https://insidethemachine.ai/setups/one-api.md): LLM API management and distribution gateway.
- [Portkey Gateway](https://insidethemachine.ai/setups/portkey-gateway.md): Fast AI gateway with guardrails and fallbacks.
- [Bifrost](https://insidethemachine.ai/setups/bifrost.md): High-performance LLM and MCP gateway.
- [Plano](https://insidethemachine.ai/setups/plano.md): AI-native proxy with smart LLM routing.
- [LLMRouter](https://insidethemachine.ai/setups/llmrouter.md): Research library of LLM routing methods.
- [Envoy AI Gateway](https://insidethemachine.ai/setups/envoy-ai-gateway.md): Envoy-based gateway for generative AI services.
- [NVIDIA LLM Router](https://insidethemachine.ai/setups/nvidia-llm-router.md): Routes each prompt to the best-fit model.
- [NVIDIA PAIR](https://insidethemachine.ai/setups/nvidia-pair.md): Shares AI requests across the computers on your home network.

## MCP servers & tools

- [MCP Servers (official)](https://insidethemachine.ai/setups/mcp-servers.md): Standard plug-in tools for agents. [runbook]
- [MCP Python SDK](https://insidethemachine.ai/setups/mcp-python-sdk.md): Official Python SDK for MCP servers and clients.
- [LLM CLI](https://insidethemachine.ai/setups/llm-cli.md): CLI and Python library for any LLM, local or cloud.
- [MCP Inspector](https://insidethemachine.ai/setups/mcp-inspector.md): Visual tester for MCP servers.
- [n8n](https://insidethemachine.ai/setups/n8n.md): Workflow automation with AI nodes, self-hostable.
- [Firecrawl](https://insidethemachine.ai/setups/firecrawl.md): Turn websites into LLM-ready data.
- [Awesome MCP Servers](https://insidethemachine.ai/setups/awesome-mcp-servers.md): Big curated list of MCP servers.
- [Crawl4AI](https://insidethemachine.ai/setups/crawl4ai.md): Open-source crawler that outputs clean markdown.
- [Context7](https://insidethemachine.ai/setups/context7.md): Up-to-date library docs for coding agents.
- [Chrome DevTools MCP](https://insidethemachine.ai/setups/chrome-devtools-mcp.md): Chrome DevTools as an MCP server.
- [SearXNG](https://insidethemachine.ai/setups/searxng.md): Self-hosted private metasearch engine.
- [Playwright MCP](https://insidethemachine.ai/setups/playwright-mcp.md): Browser automation MCP server.
- [GitHub MCP Server](https://insidethemachine.ai/setups/github-mcp-server.md): GitHub's official MCP server.
- [Serena](https://insidethemachine.ai/setups/serena.md): Semantic code retrieval and editing over MCP.

## Chat UIs & front-ends

- [Open WebUI](https://insidethemachine.ai/setups/open-webui.md): A ChatGPT-style app for your local models. [runbook]
- [NextChat](https://insidethemachine.ai/setups/nextchat.md): Lightweight cross-platform chat client.
- [LobeChat](https://insidethemachine.ai/setups/lobechat.md): Agent workspace and chat UI.
- [Cherry Studio](https://insidethemachine.ai/setups/cherry-studio.md): Desktop AI studio for many providers.
- [text-generation-webui](https://insidethemachine.ai/setups/text-generation-webui.md): Desktop app for local LLMs (text-generation-webui).
- [LibreChat](https://insidethemachine.ai/setups/librechat.md): Self-hosted multi-provider ChatGPT clone.
- [Jan](https://insidethemachine.ai/setups/jan.md): Offline ChatGPT alternative for your desktop.
- [Chatbox](https://insidethemachine.ai/setups/chatbox.md): Desktop and mobile AI client.
- [SillyTavern](https://insidethemachine.ai/setups/sillytavern.md): Power-user chat and roleplay front-end.
- [Open-LLM-VTuber](https://insidethemachine.ai/setups/open-llm-vtuber.md): Voice chat with an animated avatar, locally.
- [HF Chat UI](https://insidethemachine.ai/setups/hf-chat-ui.md): The open code behind HuggingChat.
- [big-AGI](https://insidethemachine.ai/setups/big-agi.md): Advanced multi-model chat suite.
- [Enchanted](https://insidethemachine.ai/setups/enchanted.md): Native macOS/iOS app for self-hosted models.
- [llama.vscode](https://insidethemachine.ai/setups/llama-vscode.md): Local code completion in VS Code via llama.cpp.

## Voice: speech-to-text & TTS

- [whisper.cpp](https://insidethemachine.ai/setups/whisper-cpp.md): Speech-to-text that runs on your machine. [runbook]
- [MLX-Audio](https://insidethemachine.ai/setups/mlx-audio.md): TTS, STT and speech-to-speech on MLX.
- [WhisperKit](https://insidethemachine.ai/setups/whisperkit.md): On-device speech AI for Apple Silicon (WhisperKit).
- [Parakeet MLX](https://insidethemachine.ai/setups/parakeet-mlx.md): NVIDIA Parakeet speech recognition on MLX.
- [Whisper](https://insidethemachine.ai/setups/whisper.md): OpenAI's original speech recognition model.
- [ChatTTS](https://insidethemachine.ai/setups/chattts.md): Conversational text-to-speech model.
- [Handy](https://insidethemachine.ai/setups/handy.md): Offline push-to-talk dictation app.
- [Fish Speech](https://insidethemachine.ai/setups/fish-speech.md): Open-source text-to-speech with voice cloning.
- [Chatterbox](https://insidethemachine.ai/setups/chatterbox.md): Open-source expressive TTS.
- [faster-whisper](https://insidethemachine.ai/setups/faster-whisper.md): Whisper transcription, faster, via CTranslate2.
- [WhisperX](https://insidethemachine.ai/setups/whisperx.md): Whisper with word timestamps and speaker labels.
- [CosyVoice](https://insidethemachine.ai/setups/cosyvoice.md): Multilingual voice generation model.
- [Dia](https://insidethemachine.ai/setups/dia.md): TTS that generates realistic dialogue.
- [NeMo (Parakeet)](https://insidethemachine.ai/setups/nemo-parakeet.md): NVIDIA NeMo speech models (incl. Parakeet).

## Image & video generation

- [stable-diffusion.cpp](https://insidethemachine.ai/setups/stable-diffusion-cpp.md): Image and video diffusion in pure C/C++.
- [mflux](https://insidethemachine.ai/setups/mflux.md): MLX-native image and video models for Mac.
- [Qwen-Image 2.1](https://insidethemachine.ai/setups/qwen-image-2-1.md): Qwen's open image generation and editing model.
- [Draw Things](https://insidethemachine.ai/setups/draw-things.md): Community repo for the Draw Things Mac/iOS app.
- [Stable Diffusion WebUI](https://insidethemachine.ai/setups/stable-diffusion-webui.md): The classic Stable Diffusion web UI.
- [ComfyUI](https://insidethemachine.ai/setups/comfyui.md): Node-based GUI and backend for diffusion models.
- [Fooocus](https://insidethemachine.ai/setups/fooocus.md): Prompt-first, low-setup image generator.
- [Diffusers](https://insidethemachine.ai/setups/diffusers.md): PyTorch library for image, video and audio diffusion.
- [Open-Sora](https://insidethemachine.ai/setups/open-sora.md): Open video generation models.
- [InvokeAI](https://insidethemachine.ai/setups/invokeai.md): Professional creative studio for diffusion.
- [Core ML Stable Diffusion](https://insidethemachine.ai/setups/core-ml-stable-diffusion.md): Stable Diffusion on Core ML for Apple Silicon.
- [Wan 2.2](https://insidethemachine.ai/setups/wan-2-2.md): Open video generation models (Wan 2.2).
- [Wan 2.1](https://insidethemachine.ai/setups/wan-2-1.md): Open video generation models (Wan 2.1).
- [ComfyUI Manager](https://insidethemachine.ai/setups/comfyui-manager.md): Install and manage ComfyUI custom nodes.

## Fine-tuning

- [MLX-LM-LoRA](https://insidethemachine.ai/setups/mlx-lm-lora.md): LoRA and full fine-tuning on MLX.
- [Unsloth](https://insidethemachine.ai/setups/unsloth.md): Fast, low-memory fine-tuning with a local UI.
- [LLaMA-Factory](https://insidethemachine.ai/setups/llama-factory.md): Fine-tune 100+ LLMs and VLMs from one tool.
- [nanoGPT](https://insidethemachine.ai/setups/nanogpt.md): The simplest repo to train small GPTs.
- [nanochat](https://insidethemachine.ai/setups/nanochat.md): Train a small ChatGPT end to end on a budget.
- [Open R1](https://insidethemachine.ai/setups/open-r1.md): Open reproduction of DeepSeek-R1 training.
- [verl](https://insidethemachine.ai/setups/verl.md): Reinforcement-learning post-training framework.
- [PEFT](https://insidethemachine.ai/setups/peft.md): LoRA and other parameter-efficient fine-tuning.
- [TRL](https://insidethemachine.ai/setups/trl.md): Train models with SFT, DPO and RL.
- [ms-swift](https://insidethemachine.ai/setups/ms-swift.md): Fine-tune 600+ LLMs with PEFT or full training.
- [Axolotl](https://insidethemachine.ai/setups/axolotl.md): Config-driven fine-tuning toolkit.
- [OpenRLHF](https://insidethemachine.ai/setups/openrlhf.md): Scalable RLHF and agentic RL on Ray.
- [Oumi](https://insidethemachine.ai/setups/oumi.md): Fine-tune, evaluate and deploy open models.
- [MergeKit](https://insidethemachine.ai/setups/mergekit.md): Merge model weights into new models.

## Quantization

- [bitsandbytes](https://insidethemachine.ai/setups/bitsandbytes.md): 4-bit and 8-bit quantization for PyTorch.
- [Core ML Tools](https://insidethemachine.ai/setups/core-ml-tools.md): Convert and compress models for Core ML.
- [TensorRT Model Optimizer](https://insidethemachine.ai/setups/tensorrt-model-optimizer.md): NVIDIA quantization, pruning and distillation.
- [LLM Compressor](https://insidethemachine.ai/setups/llm-compressor.md): Compress models for vLLM serving.
- [Optimum](https://insidethemachine.ai/setups/optimum.md): Hardware-optimized inference and quantization for HF models.
- [torchao](https://insidethemachine.ai/setups/torchao.md): PyTorch-native quantization.
- [ExLlamaV3](https://insidethemachine.ai/setups/exllamav3.md): Fast EXL3 quantization and inference on consumer GPUs.
- [AutoRound](https://insidethemachine.ai/setups/autoround.md): Accurate low-bit post-training quantization.
- [AQLM](https://insidethemachine.ai/setups/aqlm.md): Extreme compression with additive quantization.
- [GPTQModel](https://insidethemachine.ai/setups/gptqmodel.md): GPTQ quantization toolkit across GPU vendors.
- [Optimum Quanto](https://insidethemachine.ai/setups/optimum-quanto.md): Simple PyTorch quantization backend.

## Evals & benchmarks

- [ThinkingBox](https://insidethemachine.ai/setups/thinkingbox.md): Runs agents against MCP tools and checks what they really did.
- [promptfoo](https://insidethemachine.ai/setups/promptfoo.md): Test and red-team prompts, agents and RAG.
- [OpenAI Evals](https://insidethemachine.ai/setups/openai-evals.md): Framework and registry for evaluating LLMs.
- [DeepEval](https://insidethemachine.ai/setups/deepeval.md): Unit-test style evaluation for LLM apps.
- [Ragas](https://insidethemachine.ai/setups/ragas.md): Metrics for evaluating RAG pipelines.
- [LM Evaluation Harness](https://insidethemachine.ai/setups/lm-evaluation-harness.md): The standard harness for academic LLM benchmarks.
- [Gorilla / BFCL](https://insidethemachine.ai/setups/gorilla-bfcl.md): Function-calling models and the Berkeley tool-use leaderboard.
- [OpenCompass](https://insidethemachine.ai/setups/opencompass.md): Large evaluation platform across many benchmarks.
- [SWE-bench](https://insidethemachine.ai/setups/swe-bench.md): Benchmark of real GitHub issues for coding agents.
- [simple-evals](https://insidethemachine.ai/setups/simple-evals.md): OpenAI's lightweight reference evals.
- [LMMs-Eval](https://insidethemachine.ai/setups/lmms-eval.md): Evaluation toolkit for multimodal models.
- [Inspect AI](https://insidethemachine.ai/setups/inspect-ai.md): UK AISI framework for LLM and agent evals.
- [Terminal-Bench](https://insidethemachine.ai/setups/terminal-bench.md): Benchmark of hard tasks in a real terminal.
- [LightEval](https://insidethemachine.ai/setups/lighteval.md): Hugging Face's multi-backend eval toolkit.

## Scaffolds & templates

- [AGENTS.md](https://insidethemachine.ai/setups/agents-md.md): A README written for AI agents. [runbook]
- [ClawHub](https://insidethemachine.ai/setups/clawhub.md): Skill and plugin registry for OpenClaw.
- [Superpowers](https://insidethemachine.ai/setups/superpowers.md): Agent skills library and dev methodology.
- [Anthropic Skills](https://insidethemachine.ai/setups/anthropic-skills.md): Anthropic's public Agent Skills examples.
- [Spec Kit](https://insidethemachine.ai/setups/spec-kit.md): Spec-driven development toolkit for agents.
- [OpenSpec](https://insidethemachine.ai/setups/openspec.md): Lightweight spec-driven workflow for coding agents.
- [Awesome Claude Code](https://insidethemachine.ai/setups/awesome-claude-code.md): Curated Claude Code commands, hooks and workflows.
- [BMAD Method](https://insidethemachine.ai/setups/bmad-method.md): Agile multi-agent development method.
- [Awesome Cursor Rules](https://insidethemachine.ai/setups/awesome-cursor-rules.md): Collection of agent rule files.
- [wshobson agents](https://insidethemachine.ai/setups/wshobson-agents.md): Multi-harness agent plugin marketplace.
- [Claude Code Templates](https://insidethemachine.ai/setups/claude-code-templates.md): CLI to install agent configs and templates.
- [Vercel Agent Skills](https://insidethemachine.ai/setups/vercel-agent-skills.md): Vercel's official agent skills.
- [Task Master](https://insidethemachine.ai/setups/task-master.md): Task-management system for coding agents.
- [SOUL.md (persona file)](https://insidethemachine.ai/setups/soul-md.md): A file that sets your agent's identity and voice.

## Observability

- [Langfuse](https://insidethemachine.ai/setups/langfuse.md): Open-source tracing and evals for LLM apps.
- [MLflow](https://insidethemachine.ai/setups/mlflow.md): ML and LLM lifecycle platform with tracing.
- [Opik](https://insidethemachine.ai/setups/opik.md): Trace, evaluate and monitor LLM apps.
- [Phoenix](https://insidethemachine.ai/setups/phoenix.md): Open-source LLM tracing and evaluation.
- [Evidently](https://insidethemachine.ai/setups/evidently.md): Evaluate and monitor ML and LLM systems.
- [OpenLLMetry](https://insidethemachine.ai/setups/openllmetry.md): OpenTelemetry instrumentation for LLM apps.
- [Helicone](https://insidethemachine.ai/setups/helicone.md): LLM observability via a one-line proxy.
- [AgentOps](https://insidethemachine.ai/setups/agentops.md): Monitoring and cost tracking for agents.
- [Agenta](https://insidethemachine.ai/setups/agenta.md): Prompt management, evals and observability.
- [Logfire](https://insidethemachine.ai/setups/logfire.md): Observability for LLM and agent systems.
- [OpenLIT](https://insidethemachine.ai/setups/openlit.md): OpenTelemetry-native tracing and guardrails.
- [Weave](https://insidethemachine.ai/setups/weave.md): W&B toolkit for tracing and evaluating AI apps.

## Hardware & system utilities

- [Apple container](https://insidethemachine.ai/setups/apple-container.md): Run Linux containers natively on a Mac.
- [Stats](https://insidethemachine.ai/setups/stats.md): macOS menu-bar system monitor.
- [llmfit](https://insidethemachine.ai/setups/llmfit.md): One command to see which models fit your hardware.
- [nvtop](https://insidethemachine.ai/setups/nvtop.md): GPU monitor for Apple, AMD, Intel and NVIDIA.
- [nvitop](https://insidethemachine.ai/setups/nvitop.md): Interactive NVIDIA GPU process viewer.
- [GPUStack](https://insidethemachine.ai/setups/gpustack.md): GPU cluster manager for model serving.
- [NVIDIA Container Toolkit](https://insidethemachine.ai/setups/nvidia-container-toolkit.md): Use NVIDIA GPUs inside containers.
- [mactop](https://insidethemachine.ai/setups/mactop.md): Apple Silicon CPU/GPU/power monitor in the terminal.
- [gguf-parser](https://insidethemachine.ai/setups/gguf-parser.md): Inspect GGUF files and estimate memory use.

## Optional

- [YouTube: Inside The Machine](https://www.youtube.com/@InsideTheMachine-s2u)


---

---
title: "Zero to working local AI"
slug: start
kind: runbook
verified_on: 2026-10-15
status: "Commands verified against official docs on 2026-10-15; not yet run end-to-end on the Mac Studio test rig unless marked mac_studio_tested: true."
platform_priority: ["macos-apple-silicon", "linux", "windows"]
steps: 5
json: https://insidethemachine.ai/start.json
catalog: https://insidethemachine.ai/api/index.json
---

# Zero to working local AI

> Executable runbook. Run steps in order; each has goal, commands per platform, verify (with expected output) and rollback. Commands verified against official docs on 2026-10-15; not yet run end-to-end on the Mac Studio test rig unless marked mac_studio_tested: true.

## Bootstrap prompt

Paste this into your agent once step 3 works:

```text
You are my local AI setup agent. Work only inside ~/itm-agent. Ask before deleting anything, spending money, or sending anything outside this machine.

Context: a local model server is already running (Ollama at http://localhost:11434/v1 or LM Studio at http://localhost:1234/v1).

1. Read https://insidethemachine.ai/start.md and https://insidethemachine.ai/llms.txt. Use them as your runbook and catalog.
2. My goal: <describe what you want, in plain English>.
3. Split that goal into workflows (for example research, writing, files, documents, memory). Create ~/itm-agent with AGENTS.md (goal, workflows, rules), memory/MEMORY.md, and one folder per workflow, following step 4 of start.md.
4. For each workflow, pick the tools it needs from the catalog. For each tool, fetch https://insidethemachine.ai/setups/<slug>.md, run its install and verify steps, and write the result to memory/MEMORY.md. If a verify step fails, run that listing's rollback and tell me.
5. Set up LiteLLM routing (step 5): "fast" = my everyday local model, "smart" = the biggest model my RAM allows. Use smart only for hard tasks.
6. Finish with a short report: what you installed, what passed, what failed, and what you'd upgrade next. Note that official Gap Scores are still pending test on Mac Studio.
```

## Step 1: Check your machine

**Goal:** Know total RAM (Apple Silicon: unified memory) or GPU VRAM, and pick a model size from the fit chart.

### Fit chart

Rule of thumb (estimate, not measured): comfortable if the model file is at most 50% of RAM/VRAM, tight up to 75%, otherwise no. Context window and the OS need the rest. Sizes: https://ollama.com/library (tags pages, download sizes as listed 2026-10-15)

| RAM | qwen3.5:4b (3.3 GB) | gemma4 (6.6 GB) | gemma4:26b (16 GB) | qwen3-coder:30b (19 GB) | qwen3.5:122b (81 GB) | pick |
|---|---|---|---|---|---|---|
| 8 GB | comfortable | no | no | no | no | qwen3.5:4b |
| 16 GB | comfortable | comfortable | no | no | no | gemma4 |
| 32 GB | comfortable | comfortable | comfortable | tight | no | gemma4:26b |
| 64 GB | comfortable | comfortable | comfortable | comfortable | no | qwen3-coder:30b |
| 128 GB | comfortable | comfortable | comfortable | comfortable | tight | qwen3-coder:30b (fast) + qwen3.5:122b (smart) |

### Commands: macOS (Apple Silicon)

1. Run:

```bash
sysctl -n hw.memsize | awk '{printf "%.0f GB unified memory\n", $1/1073741824}'
```

2. Run:

```bash
system_profiler SPHardwareDataType | grep -E 'Chip|Memory'
```

### Commands: Linux

1. Run:

```bash
free -g | awk '/Mem:/{print $2" GB RAM"}'
```

2. Run:

```bash
nvidia-smi --query-gpu=name,memory.total --format=csv   # NVIDIA GPUs only
```

### Commands: Windows

1. Run:

```bash
(Get-CimInstance Win32_ComputerSystem).TotalPhysicalMemory/1GB   # PowerShell
```

### Verify

1. Expect: prints a byte count; 128GB Mac Studio ≈ 137438953472

```bash
sysctl -n hw.memsize
```

### Rollback

1. Run:

```bash
# read-only step; nothing to undo
```

Guides: Machines: what to buy or what yours can run -> https://insidethemachine.ai/machines.md (JSON: https://insidethemachine.ai/machines.json); Models vs memory: what fits your RAM -> https://insidethemachine.ai/models.md (JSON: https://insidethemachine.ai/models.json)

Related listings: https://insidethemachine.ai/setups/mlx-lm.md, https://insidethemachine.ai/setups/llama-cpp.md

## Step 2: Pick your tool

**Goal:** A local model server is running and answers a prompt.

### Commands: macOS (Apple Silicon)

1. Option A (recommended for agents): Ollama:

```bash
brew install ollama   # or: curl -fsSL https://ollama.com/install.sh | sh   (or the Mac app from ollama.com/download)
```

2. Ollama docs: agents and coding tools should get at least 64000 tokens of context:

```bash
ollama serve   # skip if the Ollama app is already running; for agents use: OLLAMA_CONTEXT_LENGTH=64000 ollama serve
```

3. Run:

```bash
ollama pull gemma4   # pick your size from the fit chart, e.g. qwen3.5:4b on 8GB, qwen3-coder:30b on 64GB+
```

4. Option B (GUI): LM Studio. Model search names are untested on Mac Studio:

```bash
brew install --cask lm-studio && lms get gemma-4   # lms get searches; pick a Gemma 4 or Qwen 3.5 build (--mlx for MLX on Apple Silicon)
```

5. Run:

```bash
lms server start && lms load <model-id-from-lms-ls>
```

### Commands: Linux

1. Run:

```bash
curl -fsSL https://ollama.com/install.sh | sh && ollama pull gemma4
```

### Commands: Windows

1. Run:

```bash
irm https://ollama.com/install.ps1 | iex; ollama pull gemma4
```

### Verify

1. Expect: a short greeting

```bash
ollama run gemma4 "Say hi in five words."
```

2. Expect: JSON list including gemma4 (Ollama's OpenAI-compatible endpoint)

```bash
curl -s http://localhost:11434/v1/models
```

3. Expect: model listed; PROCESSOR should read 100% GPU (per Ollama context-length docs)

```bash
ollama ps
```

4. Expect: LM Studio path: JSON model list (port 1234 is LM Studio's usual default)

```bash
curl -s http://localhost:1234/v1/models
```

### Rollback

1. Run:

```bash
ollama rm gemma4 && brew uninstall ollama
```

2. Run:

```bash
lms server stop && brew uninstall --cask lm-studio   # models live under ~/.lmstudio
```

Related listings: https://insidethemachine.ai/setups/ollama.md, https://insidethemachine.ai/setups/lm-studio.md

## Step 3: Point an agent at it

**Goal:** A harness (OpenCode, Goose, Aider or Hermes Agent) talks to the local endpoint http://localhost:11434/v1 (Ollama) or http://localhost:1234/v1 (LM Studio).

### Harness options

- **OpenCode**: Terminal coding agent; Ollama can configure it in one command. Docs: https://docs.ollama.com/integrations/opencode
- **Goose**: General agent with MCP extensions; desktop app or CLI. Docs: https://docs.ollama.com/integrations/goose
- **Aider**: Git-aware pair programmer for existing repos. Docs: https://aider.chat/docs/llms/ollama.html
- **Hermes Agent**: Nous Research agent with skills and cross-session memory. Docs: https://docs.ollama.com/integrations/hermes

### Commands: macOS (Apple Silicon)

1. OpenCode (recommended):

```bash
curl -fsSL https://opencode.ai/install | bash   # or: brew install anomalyco/tap/opencode
```

2. starts OpenCode with an inline config for the Ollama model you pick; does not overwrite ~/.config/opencode/opencode.json:

```bash
ollama launch opencode
```

3. manual alternative, format from opencode.ai/docs/providers; model ids must match GET /v1/models. Back up any existing file first:

```bash
mkdir -p ~/.config/opencode && cat > ~/.config/opencode/opencode.json <<'EOF'
{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "ollama": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Ollama (local)",
      "options": { "baseURL": "http://localhost:11434/v1" },
      "models": { "gemma4": { "name": "Gemma 4" } }
    }
  }
}
EOF
```

4. Goose: choose Configure Providers → Ollama → enter your model name:

```bash
curl -fsSL https://github.com/aaif-goose/goose/releases/download/stable/download_cli.sh | bash && goose configure
```

5. Aider: see /setups/aider:

```bash
python -m pip install aider-install && aider-install && aider --model ollama_chat/gemma4
```

6. Hermes Agent: Ollama points it at http://127.0.0.1:11434/v1:

```bash
ollama launch hermes   # or: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
```

### Verify

1. Expect: prints 'ready' using the local model (untested on Mac Studio)

```bash
opencode run "Reply with the word ready"
```

2. Expect: Goose opens a session; type: say ready

```bash
goose session -n itm-check
```

### Rollback

1. Run:

```bash
rm ~/.config/opencode/opencode.json   # restore your backup if you had one
```

2. Run:

```bash
brew uninstall opencode   # if installed via brew
```

3. Run:

```bash
# Goose / Hermes: follow uninstall steps in their docs (install scripts place a binary in your PATH)
```

Related listings: https://insidethemachine.ai/setups/aider.md, https://insidethemachine.ai/setups/ollama.md

## Step 4: Your goal becomes workflows

**Goal:** A workspace with AGENTS.md, memory/MEMORY.md, one folder per workflow and MCP tools configured.

### Default workflows

- research: fetch MCP server (uvx mcp-server-fetch)
- writing: AGENTS.md style rules
- files: filesystem MCP server
- memory: memory/MEMORY.md, upgrade to Mem0
- documents: Docling

### Commands: macOS (Apple Silicon)

1. Run:

```bash
mkdir -p ~/itm-agent/{workflows/{research,writing,files,documents},memory,tools} && cd ~/itm-agent && git init -q
```

2. Run:

```bash
cat > AGENTS.md <<'EOF'
# AGENTS.md
## Goal
<the user's goal in one sentence>
## Workflows
- research/: gather sources, save notes as markdown with URLs
- writing/: drafts; never publish or send without the user's OK
- files/: only touch files inside ~/itm-agent
- documents/: convert PDFs/Office files with `docling <file>`
## Memory
- Read memory/MEMORY.md at the start of every session; append decisions and facts at the end.
## Upgrades
- Before installing anything, read the listing at https://insidethemachine.ai/setups/<slug>.md and run its verify step.
EOF
```

3. Run:

```bash
printf '# MEMORY\n\n- %s: workspace created\n' "$(date +%F)" > memory/MEMORY.md
```

4. project-level OpenCode config (format from opencode.ai/docs/mcp-servers); replace /Users/YOU. Requires uv (brew install uv) and Node:

```bash
cat > opencode.json <<'EOF'
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "fetch": { "type": "local", "command": ["uvx", "mcp-server-fetch"], "enabled": true },
    "filesystem": { "type": "local", "command": ["npx", "-y", "@modelcontextprotocol/server-filesystem", "/Users/YOU/itm-agent"], "enabled": true }
  }
}
EOF
```

### Verify

1. Expect: AGENTS.md, memory/MEMORY.md, workflows/* folders, opencode.json

```bash
find ~/itm-agent -maxdepth 2 -not -path '*/.git*'
```

2. Expect: the agent lists the workflows (untested on Mac Studio)

```bash
cd ~/itm-agent && opencode run "Read AGENTS.md and list the workflows"
```

### Rollback

1. Run:

```bash
rm -rf ~/itm-agent   # deletes the workspace, irreversible
```

Related listings: https://insidethemachine.ai/setups/agents-md.md, https://insidethemachine.ai/setups/mcp-servers.md, https://insidethemachine.ai/setups/mem0.md, https://insidethemachine.ai/setups/docling.md

## Step 5: It builds and upgrades itself

**Goal:** The agent pulls /llms.txt, installs missing pieces using each listing's verify/rollback, routes via LiteLLM (fast vs smart), and logs a self-check.

### Commands: macOS (Apple Silicon)

1. the agent's map of what exists:

```bash
curl -s https://insidethemachine.ai/llms.txt && curl -s https://insidethemachine.ai/api/index.json
```

2. any listing as markdown:

```bash
curl -s -H 'Accept: text/markdown' https://insidethemachine.ai/setups/litellm
```

3. LiteLLM docs show pip install 'litellm[proxy]'; uv tool install is the isolated equivalent (untested on Mac Studio):

```bash
brew install uv && uv tool install 'litellm[proxy]'
```

4. 128GB example; on smaller machines map smart to the biggest model your chart allows, or to a cloud model you have a key for:

```bash
cat > ~/itm-agent/tools/litellm.yaml <<'EOF'
model_list:
  - model_name: "fast"
    litellm_params:
      model: "ollama_chat/qwen3-coder:30b"
  - model_name: "smart"
    litellm_params:
      model: "ollama_chat/qwen3.5:122b"
EOF
```

5. Run:

```bash
litellm --config ~/itm-agent/tools/litellm.yaml   # OpenAI-compatible proxy on http://0.0.0.0:4000
```

### Verify

1. Expect: OpenAI-format JSON reply

```bash
curl -s http://0.0.0.0:4000/chat/completions -H 'Content-Type: application/json' -d '{"model":"fast","messages":[{"role":"user","content":"ready?"}]}'
```

2. Expect: the agent logged what it installed and each verify result

```bash
tail -5 ~/itm-agent/memory/MEMORY.md
```

### Rollback

1. Run:

```bash
uv tool uninstall litellm && rm ~/itm-agent/tools/litellm.yaml
```

2. Run:

```bash
# for anything else the agent installed: run the rollback section of that listing's .md
```

### Self-check

Official Gap Scores are pending test on Mac Studio. Until then the agent's self-check is: did every listing's verify step pass, plus tokens/sec from `ollama run <model> --verbose` (untested on Mac Studio).

Related listings: https://insidethemachine.ai/setups/litellm.md, https://insidethemachine.ai/setups/mem0.md, https://insidethemachine.ai/setups/open-webui.md

## Hermes-style gaps: identity, instructions, and lean context

Frontier apps feel smart partly because of what surrounds the model: an identity, project rules, skills, memory and careful context management. These four parts give a local agent the same scaffolding without a million-token window.

### AGENTS.md and SOUL.md

#### AGENTS.md = how to work here

A plain markdown file of project rules your agent reads every session. Most harnesses (OpenCode, Goose, Hermes, OpenClaw) load it automatically.

- AGENTS.md: open, harness-agnostic project-instructions file (see /setups/agents-md).
- Hermes: loads AGENTS.md from the CWD at startup and subdirectories progressively; .hermes.md / HERMES.md take highest priority (docs: user-guide/features/context-files).
- OpenCode: reads AGENTS.md in the project and ~/.config/opencode/AGENTS.md globally (opencode.ai/docs/rules).
- Goose: CONTEXT_FILE_NAMES default is ["AGENTS.md", ".goosehints"] (goose-docs.ai using-goosehints).
- OpenClaw: workspace files include AGENTS.md, SOUL.md, IDENTITY, USER (docs.openclaw.ai templates); default workspace ~/.openclaw/workspace.

Template (~/itm-agent/AGENTS.md):

```markdown
# AGENTS.md
<!-- Always loaded. Keep under ~150 lines: rules + pointers, not knowledge. -->
## Project
One sentence: what this workspace is for.
## Rules
- Work only inside this folder. Ask before deleting, spending, or sending anything.
- Prefer small diffs. Run the verify step after every install.
## Map (load on demand, do not paste here)
- workflows/<name>/AGENTS.md : rules for that workflow only
- memory/MEMORY.md : read the last 30 lines at session start; append decisions
- skills/ : one folder per repeatable procedure (SKILL.md each)
## Output hygiene
- Pipe long command output through `tail -n 50` or `head -c 4000`.
- Summarize files; never print whole logs or datasets.
```

#### SOUL.md = who the agent is

A persona file: voice, values and limits. Hermes puts it first in the system prompt; OpenClaw injects it into normal sessions.

- Hermes: SOUL.md is the primary identity, slot #1 in the system prompt, loaded only from $HERMES_HOME/SOUL.md (default ~/.hermes/SOUL.md). Hermes seeds a starter file and never overwrites yours (docs: features/personality).
- OpenClaw: 'SOUL.md is where your agent's voice lives. OpenClaw injects it into normal sessions' (docs.openclaw.ai/concepts/soul). Lives in the agent workspace.
- OpenCode / Goose / Aider have no SOUL.md concept: put persona lines at the top of AGENTS.md or list SOUL.md as an extra instruction file (below).

Template (~/.hermes/SOUL.md):

```markdown
# SOUL.md
<!-- Identity, voice, boundaries. No project facts: those go in AGENTS.md. -->
You are Kit, a calm, direct assistant running on a local model.
## Voice
- Short sentences. Lead with the answer. No filler, no hype.
- Say "I don't know" and check, rather than guess.
## Values
- The user's machine and data stay local unless they say otherwise.
- Ask before irreversible actions.
## Never
- Invent numbers, benchmarks or citations.
```

### Point each harness at the files

#### Hermes

Edit ~/.hermes/SOUL.md for identity and start Hermes inside your workspace so it finds AGENTS.md. Skills live in ~/.hermes/skills.

```bash
$EDITOR ~/.hermes/SOUL.md
cd ~/itm-agent && hermes
```

- Note: Directory layout per docs: ~/.hermes/{config.yaml,SOUL.md,memories/,skills/}.

#### OpenCode

It reads AGENTS.md on its own. Add extra files like SOUL.md with one line of config.

```bash
cat > ~/itm-agent/opencode.json <<'EOF'
{
  "$schema": "https://opencode.ai/config.json",
  "instructions": ["SOUL.md", "workflows/*/AGENTS.md"]
}
EOF
```

- Note: 'instructions' accepts paths, globs and URLs; combined with AGENTS.md (opencode.ai/docs/rules). Merge with the mcp block from step 4 if you created one.

#### Goose

Goose reads AGENTS.md and .goosehints by default. Tell it about other files with one environment variable.

```bash
export CONTEXT_FILE_NAMES='["AGENTS.md", "SOUL.md", ".goosehints"]'
cd ~/itm-agent && goose session -n itm
```

- Note: Global hints: ~/.config/goose/.goosehints; local hints win over global.

#### Aider

Aider loads rule files as read-only context. Put them in its config so every session gets them.

```bash
printf 'read: [AGENTS.md, SOUL.md]\n' > ~/itm-agent/.aider.conf.yml
aider --read AGENTS.md   # one-off equivalent
```

- Note: Docs: aider.chat/docs/usage/conventions.html (read files are marked read-only and cached if prompt caching is enabled).

### Avoid context bloat

#### Keep always-loaded files lean

AGENTS.md and SOUL.md ride along on every turn, so every line costs you. Keep rules and pointers there, and nothing else.

- AGENTS.md: aim for under ~150 lines (house rule of thumb, not a harness limit)
- SOUL.md: aim for under ~40 lines

#### Skills load only when needed

Write repeatable procedures as skills: the agent sees a one-line description and opens the full text only when it needs it. Hermes calls this progressive disclosure.

- Hermes skills: on-demand documents following a progressive disclosure pattern to minimize token usage; agentskills.io compatible; stored in ~/.hermes/skills/.

Layout: skills/<name>/SKILL.md with front-matter name + description; body loaded on demand

#### Retrieve, don't stuff

Keep notes and documents on disk and let the agent search them. Pull in a few relevant chunks instead of whole files.

- memory/MEMORY.md tail + grep
- Mem0 (/setups/mem0)
- Docling to convert PDFs before retrieval (/setups/docling)
- Open WebUI knowledge bases (/setups/open-webui)

#### Compact long sessions

When a chat gets long, have the harness summarize the middle and keep the recent tail. Turn it on before the window fills.

opencode.json:

```
{
  "compaction": {
    "auto": true,
    "prune": true,
    "reserved": 10000
  }
}
```

~/.hermes/config.yaml:

```
compression:
  enabled: true
  threshold: 0.50   # compress at 50% of context limit
  target_ratio: 0.20
```

hermes (manual):

```
/compress
```

aider (manual):

```
/clear or /drop unused files
```

- Note: OpenCode prune=true removes old tool outputs (default false). Hermes: the summary model needs a context window at least as large as the main model's.

#### Trim tool output

Most bloat is logs and command output, not your words. Cap it at the source.

```bash
<cmd> 2>&1 | tail -n 50
<cmd> | head -c 4000
rg -n --max-count 20 'pattern' .
```

#### One folder per workflow

Give each workflow its own folder and its own small AGENTS.md. The agent only loads the rules for the job in front of it.

Layout: ~/itm-agent/workflows/{research,writing,files,documents}/AGENTS.md; start the harness inside the workflow folder (Hermes and OpenCode both pick up subdirectory AGENTS.md)

### Keep the local model efficient

#### Pick the right quant

A 4-bit model is about a quarter the size of 16-bit and usually close in quality. Use the fit chart and leave room for context.

- ollama default tags: 4-bit-class quants (sizes in step 1 chart)
- rule: prefer a bigger model at 4-bit over a smaller one at 8-bit when it fits (rule of thumb, untested on Mac Studio)

#### Set context length on purpose

Bigger windows eat memory fast. Give agents enough (64k) and no more.

ollama:

```bash
OLLAMA_CONTEXT_LENGTH=64000 ollama serve   # server-wide
/set parameter num_ctx 64000   # inside ollama run
API: "options": {"num_ctx": 64000}
ollama ps   # CONTEXT column shows what was allocated
```

llama.cpp:

```bash
llama-server -m model.gguf -c 65536   # -c, --ctx-size; 0 = from model
```

mlx-lm:

```bash
mlx_lm.generate --max-kv-size 65536 ...   # rotating fixed-size KV cache
```

- Note: Ollama: RAM scales with OLLAMA_NUM_PARALLEL × OLLAMA_CONTEXT_LENGTH; keep OLLAMA_NUM_PARALLEL=1 for a single agent.

#### Shrink the KV cache

The cache that holds your context can be quantized too. 8-bit halves its memory with very little quality loss.

ollama:

```bash
OLLAMA_FLASH_ATTENTION=1 OLLAMA_KV_CACHE_TYPE=q8_0 ollama serve
# values: f16 (default), q8_0 (~1/2 memory, recommended), q4_0 (~1/4, more loss at long context); global for all models
```

llama.cpp:

```bash
llama-server -m model.gguf -c 65536 -fa on -ctk q8_0 -ctv q8_0
```

- Note: llama.cpp allowed K/V types: f32, f16, bf16, q8_0, q4_0, q4_1, iq4_nl, q5_0, q5_1 (default f16).

#### Reuse the prompt

Your AGENTS.md and SOUL.md are the same every turn, so cache them instead of re-reading. Keep them stable so the cache keeps hitting.

ollama:

```bash
OLLAMA_KEEP_ALIVE=30m ollama serve   # keep the model loaded between turns
```

llama.cpp:

```bash
llama-server ... --cache-reuse 256   # reuse cached chunks via KV shifting; needs prompt caching
```

mlx-lm:

```bash
cat AGENTS.md | mlx_lm.cache_prompt --model <model> --prompt - --prompt-cache-file agents.safetensors
mlx_lm.generate --prompt-cache-file agents.safetensors --prompt "..."
```

- Note: Editing the top of an always-loaded file invalidates the cached prefix: put changing content at the end.

#### Small model first, big model when needed

Send routine turns to a fast model and hard ones to your biggest. LiteLLM gives both one address.

See: Step 5 litellm.yaml (fast / smart aliases)

- Note: Hermes can also run compression on a separate model via auxiliary.compression (model, base_url).

## Sources

- https://aider.chat/docs/llms/ollama.html
- https://aider.chat/docs/usage/conventions.html
- https://docs.litellm.ai/docs/providers/ollama
- https://docs.ollama.com/context-length
- https://docs.ollama.com/faq
- https://docs.ollama.com/integrations/goose
- https://docs.ollama.com/integrations/hermes
- https://docs.ollama.com/integrations/opencode
- https://docs.openclaw.ai/concepts/agent-workspace
- https://docs.openclaw.ai/concepts/soul
- https://github.com/aaif-goose/goose
- https://github.com/ggml-org/llama.cpp/blob/master/tools/server/README.md
- https://github.com/ml-explore/mlx-lm
- https://github.com/modelcontextprotocol/servers
- https://goose-docs.ai/docs/getting-started/providers
- https://goose-docs.ai/docs/guides/context-engineering/using-goosehints
- https://hermes-agent.nousresearch.com/docs/user-guide/configuration
- https://hermes-agent.nousresearch.com/docs/user-guide/features/context-files
- https://hermes-agent.nousresearch.com/docs/user-guide/features/personality
- https://hermes-agent.nousresearch.com/docs/user-guide/features/skills
- https://lmstudio.ai/docs/cli
- https://ollama.com/library/gemma4/tags
- https://ollama.com/library/qwen3-coder/tags
- https://ollama.com/library/qwen3.5/tags
- https://opencode.ai/docs/cli/
- https://opencode.ai/docs/config/
- https://opencode.ai/docs/mcp-servers/
- https://opencode.ai/docs/providers/
- https://opencode.ai/docs/rules/


---

# About Inside The Machine

Inside The Machine is a free, agent-first directory of everything that pushes a **local** AI stack toward frontier quality: runtimes, harnesses, memory, routing, MCP tools, document ingest, speech and scaffolds. It's narrated by **Kit**, the AI agent behind the [YouTube channel](https://www.youtube.com/@InsideTheMachine-s2u). Every page has a Human view and an Agent view. The Agent view is Markdown/JSON with exact install, verify and rollback steps that an agent can execute.

## Gap Score

The **Gap Score** (0–100) estimates how close a local setup gets to a frontier reference on the tasks it's meant for. 100 means parity with the frontier reference; 0 means it can't complete the tasks.

**Status: methodology draft. No scores have been published yet.** Every listing shows "pending test on Mac Studio" until it is measured.

### Test rig
- Mac Studio, Apple Silicon, 128GB unified memory (MLX / Metal)
- macOS version, tool version, model and quantization recorded with every run

### Planned method (v0.1, subject to change)
1. **Task suite per category.** Coding harnesses get repo tasks, memory tools get recall-across-sessions tasks, runtimes get a fixed prompt set, ingest tools get document-QA tasks, and so on.
2. **Frontier baseline.** The same tasks run against a named frontier model on the same date. The model and date are published with the score.
3. **Quality (≈60%)** is task success rate relative to the baseline.
4. **Speed and fit (≈25%)** covers tokens/sec, time-to-first-token and peak memory on the 128GB rig.
5. **Setup reliability (≈15%)** asks whether the listing's install → verify → rollback steps work unattended, run by an agent.
6. Raw results, prompts and configs are published next to each score. Re-tests are triggered by major releases.

The weights are a draft. Final weights will be published before the first score.

### Rules
- Never invent a number. Unmeasured means `null` + "pending test on Mac Studio".
- Sponsored listings are labeled `sponsored: true`, and sponsorship never changes a score.
- Facts (license, stars, commands) are verified against each project's repo/docs on the `verified_on` date.

## The Gap Report

A weekly newsletter with new scores, new setups and the week's local AI releases. Sign up with the form on the [Gap Score page](/gap-score) or the home page. Sent with beehiiv. Free, unsubscribe any time.


---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "mlx-lm"
name: "MLX LM"
category: "Runtimes / Inference"
stack_layer: "runtime"
homepage: "https://github.com/ml-explore/mlx-lm"
repo: "https://github.com/ml-explore/mlx-lm"
docs: "https://github.com/ml-explore/mlx-lm/blob/main/mlx_lm/SERVER.md"
license: "MIT"
platforms: ["macos-apple-silicon"]
mac_studio_fit: "Primary"
stars: 7310
stars_as_of: "2026-10-15"
last_push: "2026-10-10"
gap_score: null
gap_score_status: "pending test on Mac Studio"
benchmarks_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
sponsored: false
---

# MLX LM

> Apple's MLX-native way to generate, chat, fine-tune and serve LLMs on Apple silicon.

**What:** Runs LLMs natively on Apple silicon. **Why:** Built for the chip in your Mac, so you get more model per GB.

**Stack layer:** runtime (model → runtime → harness → memory → tools)

A Python package (mlx-lm) for running and fine-tuning large language models with Apple's MLX framework. Ships CLIs for generate, chat, convert/quantize, and an OpenAI-like HTTP server.

**Gap role:** Raw local inference speed and memory efficiency on Apple silicon; quantization (mlx_lm.convert -q) and KV-cache quantization (--kv-bits) let bigger models fit in unified memory.

## Gap Score

null (pending test on Mac Studio)

## Prerequisites

- Apple silicon Mac
- Python 3 with pip (a virtualenv is recommended)
- Some features (e.g. wired-memory tuning) require macOS 15+ per the README

## Install

### macOS (Apple Silicon)

1. isolated environment (recommended, not required):

```bash
python3 -m venv ~/.venvs/mlx && source ~/.venvs/mlx/bin/activate
```

2. Run:

```bash
pip install mlx-lm
```

3. Run:

```bash
# or with conda: conda install -c conda-forge mlx-lm
```

## Configure

1. starts an OpenAI-like server on localhost:8080; model downloads from Hugging Face on first run:

```bash
mlx_lm.server --model mlx-community/Mistral-7B-Instruct-v0.3-4bit
```

2. quantized KV cache for long contexts:

```bash
mlx_lm.server --model <hf_repo_or_path> --kv-bits 4 --prefill-step-size 512
```

## Verify

1. Expect: prints generated text and tokens-per-second stats

```bash
mlx_lm.generate --model mlx-community/Mistral-7B-Instruct-v0.3-4bit --prompt "hello"
```

2. Expect: JSON response with a choices[0].message.content field (server must be running)

```bash
curl -s http://localhost:8080/v1/chat/completions -H 'Content-Type: application/json' -d '{"messages":[{"role":"user","content":"Say hi"}]}'
```

## Rollback

1. Run:

```bash
pip uninstall -y mlx-lm
```

2. only if you created this venv:

```bash
rm -rf ~/.venvs/mlx
```

3. Run:

```bash
# downloaded models live in the Hugging Face cache (~/.cache/huggingface/hub); delete specific model folders to free space
```

## One-command install

Status: docs-checked (Not run: commands checked against the official docs only). The wrapper scripts are generated from the site data. Every .sh passed bash -n and shellcheck and ran in plan mode on Linux (Debian 13). Every .ps1 passed the PowerShell parser and chat.ps1 ran in plan, verify and rollback mode under PowerShell 7 on Linux with Windows calls mocked. Not run on macOS or real Windows.

```bash
curl -fsSL https://insidethemachine.ai/install/mlx-lm.sh | bash            # install, then check
curl -fsSL https://insidethemachine.ai/install/mlx-lm.sh | bash -s -- plan    # print only
curl -fsSL https://insidethemachine.ai/install/mlx-lm.sh | bash -s -- rollback --yes
```

Details and Windows: https://insidethemachine.ai/install/mlx-lm.md

## Caveats

- mlx_lm.server is documented as not recommended for production (basic security checks only).
- Port 8080 is also the default for llama.cpp's server and Open WebUI's pip install; run them on different ports.

## Benchmarks

Status: pending test on Mac Studio. Rig: Mac Studio, Apple Silicon, 128GB unified memory. No results published yet.

## Works with

- open-webui (https://insidethemachine.ai/setups/open-webui.md)
- litellm (https://insidethemachine.ai/setups/litellm.md)
- aider (https://insidethemachine.ai/setups/aider.md)

## Sources

- https://github.com/ml-explore/mlx-lm
- https://github.com/ml-explore/mlx-lm/blob/main/mlx_lm/SERVER.md


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "ollama"
name: "Ollama"
category: "Runtimes / Inference"
stack_layer: "runtime"
homepage: "https://ollama.com/"
repo: "https://github.com/ollama/ollama"
docs: "https://docs.ollama.com/"
license: "MIT"
platforms: ["macos-apple-silicon", "linux", "windows"]
mac_studio_fit: "Primary"
stars: 183257
stars_as_of: "2026-10-15"
last_push: "2026-10-15"
gap_score: null
gap_score_status: "pending test on Mac Studio"
benchmarks_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
sponsored: false
---

# Ollama

> The one-command local model runner with a REST API on port 11434.

**What:** One command to download and run a model. **Why:** The fastest way from zero to a local model.

**Stack layer:** runtime (model → runtime → harness → memory → tools)

A local model runner and server. Pull models by name, chat in the terminal, and call a local REST API. Official Python (ollama-python) and JS (ollama-js) libraries.

**Gap role:** The easiest on-ramp: model management plus a stable local API that harnesses, UIs and memory layers already support.

## Gap Score

null (pending test on Mac Studio)

## Prerequisites

- macOS, Linux or Windows

## Install

### macOS (Apple Silicon)

1. official script (README lists it for macOS):

```bash
curl -fsSL https://ollama.com/install.sh | sh
```

2. Run:

```bash
# alternatives: brew install ollama   |   brew install --cask ollama-app   |   download https://ollama.com/download/Ollama.dmg
```

### Linux

1. Run:

```bash
curl -fsSL https://ollama.com/install.sh | sh
```

### Windows

1. PowerShell:

```bash
irm https://ollama.com/install.ps1 | iex
```

## Configure

1. example model name used in the README; pick any model from ollama.com/library:

```bash
ollama pull gemma4
```

2. interactive chat:

```bash
ollama run gemma4
```

## Verify

1. Expect: prints a version string

```bash
ollama --version
```

2. Expect: JSON list of locally pulled models

```bash
curl -s http://localhost:11434/api/tags
```

3. Expect: JSON with message.content

```bash
curl -s http://localhost:11434/api/chat -d '{"model":"gemma4","messages":[{"role":"user","content":"hi"}],"stream":false}'
```

## Rollback

1. remove a model:

```bash
ollama rm gemma4
```

2. if installed via Homebrew:

```bash
brew uninstall ollama   # or: brew uninstall --cask ollama-app
```

3. deletes all downloaded models and keys; irreversible:

```bash
rm -rf ~/.ollama
```

## One-command install

Status: docs-checked (Not run: commands checked against the official docs only). The wrapper scripts are generated from the site data. Every .sh passed bash -n and shellcheck and ran in plan mode on Linux (Debian 13). Every .ps1 passed the PowerShell parser and chat.ps1 ran in plan, verify and rollback mode under PowerShell 7 on Linux with Windows calls mocked. Not run on macOS or real Windows.

```bash
curl -fsSL https://insidethemachine.ai/install/ollama.sh | bash            # install, then check
curl -fsSL https://insidethemachine.ai/install/ollama.sh | bash -s -- plan    # print only
curl -fsSL https://insidethemachine.ai/install/ollama.sh | bash -s -- rollback --yes
```

Details and Windows: https://insidethemachine.ai/install/ollama.md

## Caveats

- Model names change frequently; confirm on ollama.com/library.

## Benchmarks

Status: pending test on Mac Studio. Rig: Mac Studio, Apple Silicon, 128GB unified memory. No results published yet.

## Works with

- open-webui (https://insidethemachine.ai/setups/open-webui.md)
- litellm (https://insidethemachine.ai/setups/litellm.md)
- aider (https://insidethemachine.ai/setups/aider.md)
- mem0 (https://insidethemachine.ai/setups/mem0.md)

## Sources

- https://github.com/ollama/ollama
- https://formulae.brew.sh/formula/ollama
- https://formulae.brew.sh/cask/ollama-app


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "llama-cpp"
name: "llama.cpp"
category: "Runtimes / Inference"
stack_layer: "runtime"
homepage: "https://llama.app"
repo: "https://github.com/ggml-org/llama.cpp"
docs: "https://github.com/ggml-org/llama.cpp/blob/master/docs/build.md"
license: "MIT"
platforms: ["macos-apple-silicon", "linux", "windows"]
mac_studio_fit: "Primary"
stars: 131267
stars_as_of: "2026-10-15"
last_push: "2026-10-15"
gap_score: null
gap_score_status: "pending test on Mac Studio"
benchmarks_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
sponsored: false
---

# llama.cpp

> The gold-standard C/C++ inference engine for GGUF models, with Metal as a first-class backend.

**What:** The engine behind most local AI. **Why:** Full control over speed, context and quantization.

**Stack layer:** runtime (model → runtime → harness → memory → tools)

LLM inference in C/C++. Runs GGUF models from Hugging Face, includes a CLI and an OpenAI-compatible server with a built-in web UI. README: 'Apple silicon is a first-class citizen - optimized via ARM NEON, Accelerate and Metal frameworks'.

**Gap role:** Maximum control over quantization, context and sampling; widest GGUF model coverage.

## Gap Score

null (pending test on Mac Studio)

## Prerequisites

- macOS/Linux shell or Windows PowerShell

## Install

### macOS (Apple Silicon)

1. official installer from the README:

```bash
curl -LsSf https://llama.app/install.sh | sh
```

2. Run:

```bash
# alternative: brew install llama.cpp   (Homebrew formula is at 0.6.0 as of 2026-10-15)
```

### Linux

1. Run:

```bash
curl -LsSf https://llama.app/install.sh | sh
```

### Windows

1. PowerShell:

```bash
irm https://llama.app/install.ps1 | iex
```

## Configure

1. download from Hugging Face and chat (README example):

```bash
llama cli -hf ggml-org/Qwen3.5-0.8B-GGUF
```

2. OpenAI-compatible API server + web UI:

```bash
llama serve -hf ggml-org/Qwen3.5-0.8B-GGUF
```

## Verify

1. Expect: path to the llama binary (Homebrew/older builds may expose llama-cli / llama-server instead)

```bash
command -v llama
```

2. Expect: JSON listing the loaded model (server running; 8080 is the server's usual default, check startup log)

```bash
curl -s http://localhost:8080/v1/models
```

## Rollback

1. if installed via Homebrew:

```bash
brew uninstall llama.cpp
```

2. Run:

```bash
# script install: follow uninstall instructions at https://llama.app
```

3. Run:

```bash
# -hf downloads are cached (macOS default ~/Library/Caches/llama.cpp); delete to free space
```

## One-command install

Status: docs-checked (Not run: commands checked against the official docs only). The wrapper scripts are generated from the site data. Every .sh passed bash -n and shellcheck and ran in plan mode on Linux (Debian 13). Every .ps1 passed the PowerShell parser and chat.ps1 ran in plan, verify and rollback mode under PowerShell 7 on Linux with Windows calls mocked. Not run on macOS or real Windows.

```bash
curl -fsSL https://insidethemachine.ai/install/llama-cpp.sh | bash            # install, then check
curl -fsSL https://insidethemachine.ai/install/llama-cpp.sh | bash -s -- plan    # print only
curl -fsSL https://insidethemachine.ai/install/llama-cpp.sh | bash -s -- rollback --yes
```

Details and Windows: https://insidethemachine.ai/install/llama-cpp.md

## Caveats

- CLI naming changed across versions (llama cli / llama serve vs llama-cli / llama-server); use whichever your install provides.

## Benchmarks

Status: pending test on Mac Studio. Rig: Mac Studio, Apple Silicon, 128GB unified memory. No results published yet.

## Works with

- open-webui (https://insidethemachine.ai/setups/open-webui.md)
- litellm (https://insidethemachine.ai/setups/litellm.md)
- aider (https://insidethemachine.ai/setups/aider.md)

## Sources

- https://github.com/ggml-org/llama.cpp
- https://formulae.brew.sh/formula/llama.cpp
- https://www.youtube.com/watch?v=pWu3cNd0Qyo


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "lm-studio"
name: "LM Studio"
category: "Runtimes / Inference"
stack_layer: "runtime"
homepage: "https://lmstudio.ai/"
repo: "https://github.com/lmstudio-ai/lms"
docs: "https://lmstudio.ai/docs"
license: "lms CLI: MIT (LM Studio desktop app is proprietary freeware)"
platforms: ["macos-apple-silicon", "linux", "windows"]
mac_studio_fit: "Primary"
stars: 5352
stars_as_of: "2026-10-15"
last_push: "2026-10-14"
gap_score: null
gap_score_status: "pending test on Mac Studio"
benchmarks_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
sponsored: false
---

# LM Studio

> Desktop app for discovering and running local models, plus the lms CLI and a local server.

**What:** A desktop app for local models. **Why:** Browse, download and chat with no terminal needed.

**Stack layer:** runtime (model → runtime → harness → memory → tools)

A desktop application for downloading and running local LLMs, with a CLI (lms) for scripting: status, server start/stop, list and load models.

**Gap role:** Point-and-click model management with an OpenAI-compatible local server; good for comparing GGUF vs MLX builds of the same model on a Mac.

## Gap Score

null (pending test on Mac Studio)

## Prerequisites

- LM Studio 0.2.22 or newer (ships lms)

## Install

### macOS (Apple Silicon)

1. Homebrew cask (0.4.26 as of 2026-10-15) or download from https://lmstudio.ai/:

```bash
brew install --cask lm-studio
```

2. only if `lms` is not on PATH; then open a new terminal:

```bash
npx lmstudio install-cli
```

### Linux

1. Run:

```bash
# download the Linux build from https://lmstudio.ai/ then run: npx lmstudio install-cli
```

### Windows

1. Run:

```bash
# download the installer from https://lmstudio.ai/ then run: npx lmstudio install-cli
```

## Configure

1. start the local API server:

```bash
lms server start
```

2. list downloaded models:

```bash
lms ls
```

## Verify

1. Expect: shows LM Studio status

```bash
lms status
```

2. Expect: machine-readable model list

```bash
lms ls --json
```

3. Expect: JSON model list (1234 is LM Studio's usual server port; check the app if changed)

```bash
curl -s http://localhost:1234/v1/models
```

## Rollback

1. Run:

```bash
lms server stop
```

2. if installed via Homebrew:

```bash
brew uninstall --cask lm-studio
```

3. Run:

```bash
# downloaded models and settings live under ~/.lmstudio; delete only if you want them gone
```

## One-command install

Status: docs-checked (Not run: commands checked against the official docs only). The wrapper scripts are generated from the site data. Every .sh passed bash -n and shellcheck and ran in plan mode on Linux (Debian 13). Every .ps1 passed the PowerShell parser and chat.ps1 ran in plan, verify and rollback mode under PowerShell 7 on Linux with Windows calls mocked. Not run on macOS or real Windows.

```bash
curl -fsSL https://insidethemachine.ai/install/lm-studio.sh | bash            # install, then check
curl -fsSL https://insidethemachine.ai/install/lm-studio.sh | bash -s -- plan    # print only
curl -fsSL https://insidethemachine.ai/install/lm-studio.sh | bash -s -- rollback --yes
```

Details and Windows: https://insidethemachine.ai/install/lm-studio.md

## Caveats

- Desktop app is not open source; only the CLI repo is.

## Benchmarks

Status: pending test on Mac Studio. Rig: Mac Studio, Apple Silicon, 128GB unified memory. No results published yet.

## Works with

- open-webui (https://insidethemachine.ai/setups/open-webui.md)
- litellm (https://insidethemachine.ai/setups/litellm.md)
- aider (https://insidethemachine.ai/setups/aider.md)

## Sources

- https://github.com/lmstudio-ai/lms
- https://formulae.brew.sh/cask/lm-studio
- https://lmstudio.ai/


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "open-webui"
name: "Open WebUI"
category: "Frontends / Chat UIs"
stack_layer: "harness"
homepage: "https://openwebui.com/"
repo: "https://github.com/open-webui/open-webui"
docs: "https://docs.openwebui.com/"
license: "Open WebUI License (includes a requirement to preserve 'Open WebUI' branding; see LICENSE and LICENSE_HISTORY)"
platforms: ["macos-apple-silicon", "linux", "windows"]
mac_studio_fit: "Primary"
stars: 155789
stars_as_of: "2026-10-15"
last_push: "2026-10-15"
gap_score: null
gap_score_status: "pending test on Mac Studio"
benchmarks_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
sponsored: false
---

# Open WebUI

> A self-hosted, ChatGPT-style interface for Ollama and any OpenAI-compatible endpoint.

**What:** A ChatGPT-style app for your local models. **Why:** Makes a local stack feel like a finished product.

**Stack layer:** harness (model → runtime → harness → memory → tools)

A self-hosted web UI for LLMs. Installs via pip, uv, Docker or Kubernetes; connects to Ollama and OpenAI-compatible APIs.

**Gap role:** Closes the UX gap with frontier chat apps: multi-model chat, RAG over documents, user accounts.

## Gap Score

null (pending test on Mac Studio)

## Prerequisites

- Python 3.11 (the README warns other versions may cause compatibility issues) OR Docker
- A model backend such as Ollama

## Install

### macOS (Apple Silicon)

1. Run:

```bash
brew install python@3.11
```

2. Run:

```bash
python3.11 -m venv ~/.venvs/openwebui && source ~/.venvs/openwebui/bin/activate
```

3. Run:

```bash
pip install open-webui
```

4. Run:

```bash
# Docker alternative (UI on port 3000):
docker run -d -p 3000:8080 --add-host=host.docker.internal:host-gateway -v open-webui:/app/backend/data --name open-webui --restart always ghcr.io/open-webui/open-webui:main
```

### Linux

1. Run:

```bash
pip install open-webui   # inside a Python 3.11 venv
```

2. Run:

```bash
# or Docker: same docker run command as macOS
```

### Windows

1. Run:

```bash
pip install open-webui   # inside a Python 3.11 venv, or use Docker Desktop with the docker run command
```

## Configure

1. pip install: UI at http://localhost:8080:

```bash
open-webui serve
```

2. Run:

```bash
# Ollama on the same machine is detected at its default address; for a remote Ollama set -e OLLAMA_BASE_URL=... on docker run
```

## Verify

1. Expect: HTTP 200 (pip) — use port 3000 for the Docker command

```bash
curl -sI http://localhost:8080 | head -1
```

2. Expect: container listed as Up (Docker install)

```bash
docker ps --filter name=open-webui
```

## Rollback

1. pip install:

```bash
pip uninstall -y open-webui && rm -rf ~/.venvs/openwebui
```

2. Docker install; the volume holds chats/users, irreversible:

```bash
docker rm -f open-webui && docker volume rm open-webui
```

## One-command install

Status: docs-checked (Not run: commands checked against the official docs only). The wrapper scripts are generated from the site data. Every .sh passed bash -n and shellcheck and ran in plan mode on Linux (Debian 13). Every .ps1 passed the PowerShell parser and chat.ps1 ran in plan, verify and rollback mode under PowerShell 7 on Linux with Windows calls mocked. Not run on macOS or real Windows.

```bash
curl -fsSL https://insidethemachine.ai/install/open-webui.sh | bash            # install, then check
curl -fsSL https://insidethemachine.ai/install/open-webui.sh | bash -s -- plan    # print only
curl -fsSL https://insidethemachine.ai/install/open-webui.sh | bash -s -- rollback --yes
```

Details and Windows: https://insidethemachine.ai/install/open-webui.md

## Caveats

- Default pip port 8080 collides with mlx_lm.server and llama.cpp's server defaults.

## Benchmarks

Status: pending test on Mac Studio. Rig: Mac Studio, Apple Silicon, 128GB unified memory. No results published yet.

## Works with

- ollama (https://insidethemachine.ai/setups/ollama.md)
- llama-cpp (https://insidethemachine.ai/setups/llama-cpp.md)
- mlx-lm (https://insidethemachine.ai/setups/mlx-lm.md)
- lm-studio (https://insidethemachine.ai/setups/lm-studio.md)
- litellm (https://insidethemachine.ai/setups/litellm.md)

## Sources

- https://github.com/open-webui/open-webui
- https://docs.openwebui.com/


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "litellm"
name: "LiteLLM"
category: "Model Routing"
stack_layer: "runtime"
homepage: "https://www.litellm.ai/"
repo: "https://github.com/BerriAI/litellm"
docs: "https://docs.litellm.ai/"
license: "See repo LICENSE (GitHub reports NOASSERTION: open-source core with a separately licensed enterprise directory)"
platforms: ["macos-apple-silicon", "linux", "windows"]
mac_studio_fit: "Primary"
stars: 61319
stars_as_of: "2026-10-15"
last_push: "2026-10-15"
gap_score: null
gap_score_status: "pending test on Mac Studio"
benchmarks_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
sponsored: false
---

# LiteLLM

> One OpenAI-format API (SDK or proxy) in front of 100+ providers, including your local models.

**What:** One API in front of every model, local or cloud. **Why:** Send easy jobs to your Mac and hard ones to the cloud.

**Stack layer:** runtime (model → runtime → harness → memory → tools)

A Python SDK and proxy server (AI gateway) that exposes many LLM providers, including Ollama, behind an OpenAI-compatible API.

**Gap role:** Model routing and fallbacks: mix local and cloud models behind one endpoint so agents don't care where a call runs.

## Gap Score

null (pending test on Mac Studio)

## Prerequisites

- uv (brew install uv) or pip
- A backend, e.g. Ollama on localhost:11434

## Install

### macOS (Apple Silicon)

1. Run:

```bash
brew install uv
```

2. Run:

```bash
uv tool install 'litellm[proxy]'
```

### Linux

1. Run:

```bash
uv tool install 'litellm[proxy]'
```

### Windows

1. Run:

```bash
uv tool install "litellm[proxy]"
```

## Configure

1. maps a local Ollama model to a proxy alias (format from LiteLLM's Ollama docs):

```bash
cat > litellm.yaml <<'EOF'
model_list:
  - model_name: "local-llama"
    litellm_params:
      model: "ollama_chat/llama3.1"
EOF
```

2. proxy on http://0.0.0.0:4000:

```bash
litellm --config litellm.yaml
```

## Verify

1. Expect: OpenAI-format JSON response; add an Authorization header if you set a master key

```bash
curl -s http://0.0.0.0:4000/chat/completions -H 'Content-Type: application/json' -d '{"model":"local-llama","messages":[{"role":"user","content":"hi"}]}'
```

## Rollback

1. Run:

```bash
uv tool uninstall litellm
```

2. Run:

```bash
rm litellm.yaml
```

## One-command install

Status: docs-checked (Not run: commands checked against the official docs only). The wrapper scripts are generated from the site data. Every .sh passed bash -n and shellcheck and ran in plan mode on Linux (Debian 13). Every .ps1 passed the PowerShell parser and chat.ps1 ran in plan, verify and rollback mode under PowerShell 7 on Linux with Windows calls mocked. Not run on macOS or real Windows.

```bash
curl -fsSL https://insidethemachine.ai/install/litellm.sh | bash            # install, then check
curl -fsSL https://insidethemachine.ai/install/litellm.sh | bash -s -- plan    # print only
curl -fsSL https://insidethemachine.ai/install/litellm.sh | bash -s -- rollback --yes
```

Details and Windows: https://insidethemachine.ai/install/litellm.md

## Caveats

- Requires `ollama pull llama3.1` (or edit the model) before the verify step.

## Benchmarks

Status: pending test on Mac Studio. Rig: Mac Studio, Apple Silicon, 128GB unified memory. No results published yet.

## Works with

- ollama (https://insidethemachine.ai/setups/ollama.md)
- mlx-lm (https://insidethemachine.ai/setups/mlx-lm.md)
- llama-cpp (https://insidethemachine.ai/setups/llama-cpp.md)
- lm-studio (https://insidethemachine.ai/setups/lm-studio.md)
- aider (https://insidethemachine.ai/setups/aider.md)
- open-webui (https://insidethemachine.ai/setups/open-webui.md)

## Sources

- https://github.com/BerriAI/litellm
- https://docs.litellm.ai/docs/providers/ollama


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "aider"
name: "Aider"
category: "Harnesses / Coding Agents"
stack_layer: "harness"
homepage: "https://aider.chat/"
repo: "https://github.com/Aider-AI/aider"
docs: "https://aider.chat/docs/llms/ollama.html"
license: "Apache-2.0"
platforms: ["macos-apple-silicon", "linux", "windows"]
mac_studio_fit: "Primary"
stars: 49567
stars_as_of: "2026-10-15"
last_push: "2026-05-22"
gap_score: null
gap_score_status: "pending test on Mac Studio"
benchmarks_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
sponsored: false
---

# Aider

> AI pair programming in your terminal that edits your git repo, and it works with local models.

**What:** A coding agent in your terminal. **Why:** Lets a local model edit real code in your repo.

**Stack layer:** harness (model → runtime → harness → memory → tools)

A terminal coding agent that maps your codebase, edits files and makes git commits. Connects to cloud models or local models via Ollama.

**Gap role:** Harness quality: repo maps and edit formats help smaller local models do real multi-file coding work.

## Gap Score

null (pending test on Mac Studio)

## Prerequisites

- Python with pip
- git
- Ollama with a pulled model for local use

## Install

### macOS (Apple Silicon)

1. Run:

```bash
python -m pip install aider-install
```

2. Run:

```bash
aider-install
```

### Linux

1. Run:

```bash
python -m pip install aider-install && aider-install
```

### Windows

1. Run:

```bash
python -m pip install aider-install; aider-install
```

## Configure

1. Run:

```bash
export OLLAMA_API_BASE=http://127.0.0.1:11434
```

2. per Aider's Ollama docs; raises context to 8k:

```bash
OLLAMA_CONTEXT_LENGTH=8192 ollama serve
```

3. docs recommend ollama_chat/ over ollama/:

```bash
cd /path/to/your/project && aider --model ollama_chat/<model>
```

## Verify

1. Expect: prints a version

```bash
aider --version
```

2. Expect: completes one turn against the local model and exits

```bash
aider --model ollama_chat/<model> --message 'list the files in this repo' 
```

## Rollback

1. aider-install installs via uv; if that fails, check `uv tool list`:

```bash
uv tool uninstall aider-chat
```

2. Run:

```bash
pip uninstall -y aider-install
```

## One-command install

Status: docs-checked (Not run: commands checked against the official docs only). The wrapper scripts are generated from the site data. Every .sh passed bash -n and shellcheck and ran in plan mode on Linux (Debian 13). Every .ps1 passed the PowerShell parser and chat.ps1 ran in plan, verify and rollback mode under PowerShell 7 on Linux with Windows calls mocked. Not run on macOS or real Windows.

```bash
curl -fsSL https://insidethemachine.ai/install/aider.sh | bash            # install, then check
curl -fsSL https://insidethemachine.ai/install/aider.sh | bash -s -- plan    # print only
curl -fsSL https://insidethemachine.ai/install/aider.sh | bash -s -- rollback --yes
```

Details and Windows: https://insidethemachine.ai/install/aider.md

## Caveats

- Last push to the repo was 2026-05-22 (slower activity than most P0 items).

## Benchmarks

Status: pending test on Mac Studio. Rig: Mac Studio, Apple Silicon, 128GB unified memory. No results published yet.

## Works with

- ollama (https://insidethemachine.ai/setups/ollama.md)
- litellm (https://insidethemachine.ai/setups/litellm.md)
- lm-studio (https://insidethemachine.ai/setups/lm-studio.md)
- llama-cpp (https://insidethemachine.ai/setups/llama-cpp.md)
- mlx-lm (https://insidethemachine.ai/setups/mlx-lm.md)

## Sources

- https://github.com/Aider-AI/aider
- https://aider.chat/docs/llms/ollama.html


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "hermes-agent"
name: "Hermes Agent"
category: "Harnesses / Personal Agents"
stack_layer: "harness"
homepage: "https://hermes-agent.nousresearch.com/"
repo: "https://github.com/NousResearch/hermes-agent"
docs: "https://hermes-agent.nousresearch.com/docs/"
license: "MIT"
platforms: ["macos-apple-silicon", "linux", "windows"]
mac_studio_fit: "Strong"
stars: 254039
stars_as_of: "2026-10-15"
last_push: "2026-10-15"
gap_score: null
gap_score_status: "pending test on Mac Studio"
benchmarks_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
sponsored: false
---

# Hermes Agent

> Nous Research's self-improving agent: skills, cross-session memory and a messaging gateway, pointed at your local model.

**What:** A personal agent that learns skills and remembers you. **Why:** Your local model gets a learning loop, not just a chat box.

**Stack layer:** harness (model → runtime → harness → memory → tools)

A general-purpose agent with a terminal UI and a gateway for Telegram, Discord, Slack, WhatsApp, Signal and Email. It creates skills from experience, keeps agent-curated memory, searches past sessions, and runs scheduled automations. Works with any OpenAI-compatible endpoint, including Ollama.

**Gap role:** Harness + memory: a built-in learning loop (skills and cross-session recall) is one of the frontier-app features a bare local model lacks.

## Gap Score

null (pending test on Mac Studio)

## Prerequisites

- A local OpenAI-compatible server (Ollama at http://127.0.0.1:11434/v1)
- A model with tool calling and a large context window (Ollama recommends at least 64000 tokens for agents)

## Install

### macOS (Apple Silicon)

1. Run:

```bash
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
```

2. reload your shell so `hermes` is on PATH:

```bash
source ~/.zshrc
```

### Linux

1. Run:

```bash
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash && source ~/.bashrc
```

### Windows

1. PowerShell:

```bash
iex (irm https://hermes-agent.nousresearch.com/install.ps1)
```

## Configure

1. easiest path: Ollama installs Hermes if needed, points it at http://127.0.0.1:11434/v1 and sets your model as primary:

```bash
ollama launch hermes
```

2. manual path: choose More providers → Custom endpoint → http://127.0.0.1:11434/v1, leave API key blank:

```bash
hermes model
```

3. Ollama docs: agents need at least 64000 tokens of context:

```bash
OLLAMA_CONTEXT_LENGTH=64000 ollama serve
```

4. optional: chat with it from Telegram/Discord/Slack/WhatsApp/Signal/Email:

```bash
hermes gateway setup
```

## Verify

1. Expect: diagnostics report with no blocking errors

```bash
hermes doctor
```

2. Expect: TUI opens; a one-line prompt gets an answer from the local model

```bash
hermes
```

## Rollback

1. preview what will be removed:

```bash
hermes uninstall --dry-run
```

2. default keeps config and data in ~/.hermes; add --full to remove data too (destructive, run `hermes backup` first):

```bash
hermes uninstall
```

## One-command install

Status: docs-checked (Not run: commands checked against the official docs only). The wrapper scripts are generated from the site data. Every .sh passed bash -n and shellcheck and ran in plan mode on Linux (Debian 13). Every .ps1 passed the PowerShell parser and chat.ps1 ran in plan, verify and rollback mode under PowerShell 7 on Linux with Windows calls mocked. Not run on macOS or real Windows.

```bash
curl -fsSL https://insidethemachine.ai/install/hermes-agent.sh | bash            # install, then check
curl -fsSL https://insidethemachine.ai/install/hermes-agent.sh | bash -s -- plan    # print only
curl -fsSL https://insidethemachine.ai/install/hermes-agent.sh | bash -s -- rollback --yes
```

Details and Windows: https://insidethemachine.ai/install/hermes-agent.md

## Caveats

- Large, fast-moving project (multiple pushes per day); commands can change, re-check the docs.
- Nous Portal is an optional paid provider; this listing covers the local Ollama path only.
- Not yet run on the Mac Studio test rig.

## Benchmarks

Status: pending test on Mac Studio. Rig: Mac Studio, Apple Silicon, 128GB unified memory. No results published yet.

## Works with

- ollama (https://insidethemachine.ai/setups/ollama.md)
- lm-studio (https://insidethemachine.ai/setups/lm-studio.md)
- litellm (https://insidethemachine.ai/setups/litellm.md)
- mcp-servers (https://insidethemachine.ai/setups/mcp-servers.md)
- agents-md (https://insidethemachine.ai/setups/agents-md.md)

## Sources

- https://github.com/NousResearch/hermes-agent
- https://hermes-agent.nousresearch.com/docs/getting-started/installation
- https://hermes-agent.nousresearch.com/docs/getting-started/updating
- https://docs.ollama.com/integrations/hermes
- https://docs.ollama.com/context-length


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "mem0"
name: "Mem0"
category: "Memory"
stack_layer: "memory"
homepage: "https://mem0.ai/"
repo: "https://github.com/mem0ai/mem0"
docs: "https://docs.mem0.ai/cookbooks/companions/local-companion-ollama"
license: "Apache-2.0"
platforms: ["macos-apple-silicon", "linux", "windows"]
mac_studio_fit: "Primary"
stars: 67233
stars_as_of: "2026-10-15"
last_push: "2026-10-14"
gap_score: null
gap_score_status: "pending test on Mac Studio"
benchmarks_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
sponsored: false
---

# Mem0

> A memory layer for agents that can run fully local with Ollama and Qdrant.

**What:** Long-term memory for your agent. **Why:** Your assistant remembers you between sessions.

**Stack layer:** memory (model → runtime → harness → memory → tools)

An open-source memory layer (Python mem0ai / npm mem0ai) that extracts, stores and retrieves memories for agents. There's a hosted platform plus OSS; this listing covers OSS, local only.

**Gap role:** Persistent, personalized memory across sessions, one of the biggest felt gaps between local agents and frontier assistants.

## Gap Score

null (pending test on Mac Studio)

## Prerequisites

- Python 3 + pip
- Ollama with an LLM and an embedding model
- Docker for Qdrant (vector store)

## Install

### macOS (Apple Silicon)

1. Run:

```bash
pip install mem0ai
```

2. models used in Mem0's local Ollama cookbook:

```bash
ollama pull llama3.1:latest && ollama pull nomic-embed-text:latest
```

3. local Qdrant vector store:

```bash
docker run -d -p 6333:6333 --name qdrant qdrant/qdrant
```

## Configure

1. config adapted verbatim from Mem0's 'Self-Hosted AI Companion' cookbook:

```bash
cat > mem0_local.py <<'EOF'
from mem0 import Memory
config = {
  "vector_store": {"provider": "qdrant", "config": {"collection_name": "test", "host": "localhost", "port": 6333, "embedding_model_dims": 768}},
  "llm": {"provider": "ollama", "config": {"model": "llama3.1:latest", "temperature": 0, "max_tokens": 2000, "ollama_base_url": "http://localhost:11434"}},
  "embedder": {"provider": "ollama", "config": {"model": "nomic-embed-text:latest", "ollama_base_url": "http://localhost:11434"}},
}
m = Memory.from_config(config)
m.add("I'm visiting Paris", user_id="john")
print(m.get_all(filters={"user_id": "john"}))
EOF
```

## Verify

1. Expect: prints a results list containing a memory about visiting Paris

```bash
python mem0_local.py
```

## Rollback

1. Run:

```bash
pip uninstall -y mem0ai
```

2. deletes stored vectors unless you mounted a volume:

```bash
docker rm -f qdrant
```

3. Run:

```bash
rm mem0_local.py
```

## One-command install

Status: docs-checked (Not run: commands checked against the official docs only). The wrapper scripts are generated from the site data. Every .sh passed bash -n and shellcheck and ran in plan mode on Linux (Debian 13). Every .ps1 passed the PowerShell parser and chat.ps1 ran in plan, verify and rollback mode under PowerShell 7 on Linux with Windows calls mocked. Not run on macOS or real Windows.

```bash
curl -fsSL https://insidethemachine.ai/install/mem0.sh | bash            # install, then check
curl -fsSL https://insidethemachine.ai/install/mem0.sh | bash -s -- plan    # print only
curl -fsSL https://insidethemachine.ai/install/mem0.sh | bash -s -- rollback --yes
```

Details and Windows: https://insidethemachine.ai/install/mem0.md

## Caveats

- embedding_model_dims must match your embedding model (768 for nomic-embed-text per the cookbook).

## Benchmarks

Status: pending test on Mac Studio. Rig: Mac Studio, Apple Silicon, 128GB unified memory. No results published yet.

## Works with

- ollama (https://insidethemachine.ai/setups/ollama.md)
- litellm (https://insidethemachine.ai/setups/litellm.md)

## Sources

- https://github.com/mem0ai/mem0
- https://docs.mem0.ai/cookbooks/companions/local-companion-ollama


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "mcp-servers"
name: "MCP Servers (official)"
category: "MCP / Tools"
stack_layer: "tools"
homepage: "https://modelcontextprotocol.io/"
repo: "https://github.com/modelcontextprotocol/servers"
docs: "https://modelcontextprotocol.io/"
license: "See repo LICENSE (GitHub reports NOASSERTION)"
platforms: ["macos-apple-silicon", "linux", "windows"]
mac_studio_fit: "Primary"
stars: 91283
stars_as_of: "2026-10-15"
last_push: "2026-10-13"
gap_score: null
gap_score_status: "pending test on Mac Studio"
benchmarks_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
sponsored: false
---

# MCP Servers (official)

> Reference Model Context Protocol servers: memory, git, filesystem and more, ready to plug into any MCP client.

**What:** Standard plug-in tools for agents. **Why:** Gives a local agent hands: files, git and more.

**Stack layer:** tools (model → runtime → harness → memory → tools)

The official collection of reference MCP server implementations. TypeScript servers run via npx, Python servers via uvx or pip.

**Gap role:** Tool use: gives local agents the same standardized tools (files, git, memory, fetch) frontier assistants use.

## Gap Score

null (pending test on Mac Studio)

## Prerequisites

- Node.js (for npx servers)
- uv/uvx (brew install uv) for Python servers
- An MCP-capable client

## Install

### macOS (Apple Silicon)

1. Run:

```bash
brew install node uv
```

2. runs the Memory server (stdio):

```bash
npx -y @modelcontextprotocol/server-memory
```

3. runs the Git server; or: pip install mcp-server-git && python -m mcp_server_git:

```bash
uvx mcp-server-git
```

## Configure

1. the README's client example uses Claude Desktop; other clients use the same command/args shape:

```bash
# add to your MCP client's config, e.g.
{
  "mcpServers": {
    "memory": {"command": "npx", "args": ["-y", "@modelcontextprotocol/server-memory"]}
  }
}
```

## Verify

1. Expect: MCP Inspector opens in your browser and lists the server's tools

```bash
npx @modelcontextprotocol/inspector npx -y @modelcontextprotocol/server-memory
```

## Rollback

1. Run:

```bash
# remove the server entry from your MCP client config and restart the client
```

2. Run:

```bash
npm cache clean --force   # optional, clears npx downloads
```

## One-command install

Status: docs-checked (Not run: commands checked against the official docs only). The wrapper scripts are generated from the site data. Every .sh passed bash -n and shellcheck and ran in plan mode on Linux (Debian 13). Every .ps1 passed the PowerShell parser and chat.ps1 ran in plan, verify and rollback mode under PowerShell 7 on Linux with Windows calls mocked. Not run on macOS or real Windows.

```bash
curl -fsSL https://insidethemachine.ai/install/mcp-servers.sh | bash            # install, then check
curl -fsSL https://insidethemachine.ai/install/mcp-servers.sh | bash -s -- plan    # print only
curl -fsSL https://insidethemachine.ai/install/mcp-servers.sh | bash -s -- rollback --yes
```

Details and Windows: https://insidethemachine.ai/install/mcp-servers.md

## Caveats

- Reference servers are examples, not hardened production services; review each server's README.

## Benchmarks

Status: pending test on Mac Studio. Rig: Mac Studio, Apple Silicon, 128GB unified memory. No results published yet.

## Works with

- agents-md (https://insidethemachine.ai/setups/agents-md.md)

## Sources

- https://github.com/modelcontextprotocol/servers
- https://modelcontextprotocol.io/


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "whisper-cpp"
name: "whisper.cpp"
category: "Multimodal / Speech"
stack_layer: "tools"
homepage: "https://github.com/ggml-org/whisper.cpp"
repo: "https://github.com/ggml-org/whisper.cpp"
docs: "https://github.com/ggml-org/whisper.cpp#readme"
license: "MIT"
platforms: ["macos-apple-silicon", "linux", "windows"]
mac_studio_fit: "Primary"
stars: 54413
stars_as_of: "2026-10-15"
last_push: "2026-10-12"
gap_score: null
gap_score_status: "pending test on Mac Studio"
benchmarks_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
sponsored: false
---

# whisper.cpp

> Local speech-to-text with Metal GPU acceleration and optional Core ML on Apple silicon.

**What:** Speech-to-text that runs on your machine. **Why:** Talk to your agent, offline and private.

**Stack layer:** tools (model → runtime → harness → memory → tools)

A C/C++ port of OpenAI's Whisper speech recognition model. Builds with CMake; ships whisper-cli and model download scripts.

**Gap role:** Voice input: private, offline transcription that pairs with local LLMs.

## Gap Score

null (pending test on Mac Studio)

## Prerequisites

- Xcode Command Line Tools (xcode-select --install)
- CMake (brew install cmake)
- git

## Install

### macOS (Apple Silicon)

1. Run:

```bash
xcode-select --install   # skip if already installed
```

2. Run:

```bash
brew install cmake
```

3. Run:

```bash
git clone https://github.com/ggml-org/whisper.cpp.git && cd whisper.cpp
```

4. Run:

```bash
sh ./models/download-ggml-model.sh base.en
```

5. Run:

```bash
cmake -B build && cmake --build build -j --config Release
```

### Linux

1. Run:

```bash
git clone https://github.com/ggml-org/whisper.cpp.git && cd whisper.cpp && sh ./models/download-ggml-model.sh base.en && cmake -B build && cmake --build build -j --config Release
```

## Configure

1. Run:

```bash
# optional: Core ML encoder on the Apple Neural Engine; see the README's 'Core ML support' section
```

## Verify

1. Expect: prints a transcript of the bundled JFK sample

```bash
./build/bin/whisper-cli -f samples/jfk.wav
```

## Rollback

1. removes source, build and downloaded models:

```bash
cd .. && rm -rf whisper.cpp
```

## One-command install

Status: docs-checked (Not run: commands checked against the official docs only). The wrapper scripts are generated from the site data. Every .sh passed bash -n and shellcheck and ran in plan mode on Linux (Debian 13). Every .ps1 passed the PowerShell parser and chat.ps1 ran in plan, verify and rollback mode under PowerShell 7 on Linux with Windows calls mocked. Not run on macOS or real Windows.

```bash
curl -fsSL https://insidethemachine.ai/install/whisper-cpp.sh | bash            # install, then check
curl -fsSL https://insidethemachine.ai/install/whisper-cpp.sh | bash -s -- plan    # print only
curl -fsSL https://insidethemachine.ai/install/whisper-cpp.sh | bash -s -- rollback --yes
```

Details and Windows: https://insidethemachine.ai/install/whisper-cpp.md

## Caveats

- whisper-cli currently only accepts 16-bit WAV input; convert other formats first (README).

## Benchmarks

Status: pending test on Mac Studio. Rig: Mac Studio, Apple Silicon, 128GB unified memory. No results published yet.

## Works with

- ollama (https://insidethemachine.ai/setups/ollama.md)
- open-webui (https://insidethemachine.ai/setups/open-webui.md)

## Sources

- https://github.com/ggml-org/whisper.cpp


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "docling"
name: "Docling"
category: "Tools / Document Ingest"
stack_layer: "memory"
homepage: "https://github.com/docling-project/docling"
repo: "https://github.com/docling-project/docling"
docs: "https://docling-project.github.io/docling/"
license: "MIT"
platforms: ["macos-apple-silicon", "linux", "windows"]
mac_studio_fit: "Primary"
stars: 68929
stars_as_of: "2026-10-15"
last_push: "2026-10-15"
gap_score: null
gap_score_status: "pending test on Mac Studio"
benchmarks_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
sponsored: false
---

# Docling

> Turn PDFs, Office docs, Apple iWork files, audio and more into clean Markdown/JSON for RAG.

**What:** Turns documents into clean text for AI. **Why:** Better input means better answers from your docs.

**Stack layer:** memory (model → runtime → harness → memory → tools)

A document conversion toolkit (Python package and CLI) that parses many formats into structured output for gen-AI pipelines.

**Gap role:** Retrieval quality: better parsing, better RAG answers from local models.

## Gap Score

null (pending test on Mac Studio)

## Prerequisites

- Python 3.10+ (3.9 support dropped in 2.70.0)

## Install

### macOS (Apple Silicon)

1. Run:

```bash
python3 -m venv ~/.venvs/docling && source ~/.venvs/docling/bin/activate
```

2. Run:

```bash
pip install docling
```

### Linux

1. Run:

```bash
pip install docling
```

### Windows

1. Run:

```bash
pip install docling
```

## Configure

1. optional: VLM pipeline using GraniteDocling:

```bash
docling --pipeline vlm --vlm-model granite_docling https://arxiv.org/pdf/2206.01062
```

## Verify

1. Expect: writes a Markdown conversion of the paper to the current directory

```bash
docling https://arxiv.org/pdf/2206.01062
```

## Rollback

1. Run:

```bash
pip uninstall -y docling && rm -rf ~/.venvs/docling
```

## One-command install

Status: docs-checked (Not run: commands checked against the official docs only). The wrapper scripts are generated from the site data. Every .sh passed bash -n and shellcheck and ran in plan mode on Linux (Debian 13). Every .ps1 passed the PowerShell parser and chat.ps1 ran in plan, verify and rollback mode under PowerShell 7 on Linux with Windows calls mocked. Not run on macOS or real Windows.

```bash
curl -fsSL https://insidethemachine.ai/install/docling.sh | bash            # install, then check
curl -fsSL https://insidethemachine.ai/install/docling.sh | bash -s -- plan    # print only
curl -fsSL https://insidethemachine.ai/install/docling.sh | bash -s -- rollback --yes
```

Details and Windows: https://insidethemachine.ai/install/docling.md

## Caveats

- First run downloads layout models.

## Benchmarks

Status: pending test on Mac Studio. Rig: Mac Studio, Apple Silicon, 128GB unified memory. No results published yet.

## Works with

- mem0 (https://insidethemachine.ai/setups/mem0.md)
- open-webui (https://insidethemachine.ai/setups/open-webui.md)

## Sources

- https://github.com/docling-project/docling


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "agents-md"
name: "AGENTS.md"
category: "Scaffolds / Recipes"
stack_layer: "harness"
homepage: "https://agents.md/"
repo: "https://github.com/agentsmd/agents.md"
docs: "https://agents.md/"
license: "MIT"
platforms: ["macos-apple-silicon", "linux", "windows"]
mac_studio_fit: "Primary"
stars: 24944
stars_as_of: "2026-10-15"
last_push: "2026-09-10"
gap_score: null
gap_score_status: "pending test on Mac Studio"
benchmarks_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
sponsored: false
---

# AGENTS.md

> A simple open format, basically a README for coding agents, that tells them how to work in your repo.

**What:** A README written for AI agents. **Why:** Clear instructions help small models act smarter.

**Stack layer:** harness (model → runtime → harness → memory → tools)

A convention: put an AGENTS.md file at the repo root with dev environment tips, test instructions and PR rules so coding agents behave predictably.

**Gap role:** Context engineering: clear instructions let smaller local models punch above their weight in a codebase.

## Gap Score

null (pending test on Mac Studio)

## Prerequisites

- A git repository

## Install

### macOS (Apple Silicon)

1. section headings follow the official example:

```bash
cat > AGENTS.md <<'EOF'
# AGENTS.md

## Dev environment tips
- <how to install deps / run the app>

## Testing instructions
- <exact test command>

## PR instructions
- Always run lint and tests before committing.
EOF
```

## Configure

1. Run:

```bash
# point your agent at the repo; agents that support AGENTS.md read it automatically
```

## Verify

1. Expect: file exists at the repo root

```bash
test -f AGENTS.md && head -5 AGENTS.md
```

## Rollback

1. Run:

```bash
git rm AGENTS.md   # or: rm AGENTS.md
```

## One-command install

Status: docs-checked (Not run: commands checked against the official docs only). The wrapper scripts are generated from the site data. Every .sh passed bash -n and shellcheck and ran in plan mode on Linux (Debian 13). Every .ps1 passed the PowerShell parser and chat.ps1 ran in plan, verify and rollback mode under PowerShell 7 on Linux with Windows calls mocked. Not run on macOS or real Windows.

```bash
curl -fsSL https://insidethemachine.ai/install/agents-md.sh | bash            # install, then check
curl -fsSL https://insidethemachine.ai/install/agents-md.sh | bash -s -- plan    # print only
curl -fsSL https://insidethemachine.ai/install/agents-md.sh | bash -s -- rollback --yes
```

Details and Windows: https://insidethemachine.ai/install/agents-md.md

## Caveats

- Support varies by agent; check your agent's docs.

## Benchmarks

Status: pending test on Mac Studio. Rig: Mac Studio, Apple Silicon, 128GB unified memory. No results published yet.

## Works with

- aider (https://insidethemachine.ai/setups/aider.md)
- mcp-servers (https://insidethemachine.ai/setups/mcp-servers.md)

## Sources

- https://github.com/agentsmd/agents.md
- https://agents.md/


---

# Catalog entries

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "sglang"
name: "SGLang"
kind: "repo"
tier: "catalog"
category: "runtimes"
category_label: "Runtimes & inference"
stack_layer: "runtime"
homepage: "https://sglang.io"
repo: "https://github.com/sgl-project/sglang"
license: "Apache-2.0"
stars: 37175
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# SGLang

**What:** High-throughput serving for LLMs and VLMs.

**Why:** Runs open models on your own hardware.

**Category:** Runtimes & inference · **Stack layer:** runtime

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
docker pull lmsysorg/sglang:latest
```

2. [any] source: README (auto-extracted); status: unverified, not executed

```bash
uv pip install --prerelease=allow sglang
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
docker rmi lmsysorg/sglang:latest
```

2. source: derived inverse of install command

```bash
uv pip uninstall sglang
```

## Links

- Homepage: https://sglang.io
- Repo: https://github.com/sgl-project/sglang
- README: https://github.com/sgl-project/sglang#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "mlx"
name: "MLX"
kind: "repo"
tier: "catalog"
category: "runtimes"
category_label: "Runtimes & inference"
stack_layer: "runtime"
homepage: "https://ml-explore.github.io/mlx/"
repo: "https://github.com/ml-explore/mlx"
license: "MIT"
stars: 28797
last_push: "2026-10-15"
archived: false
tags: ["apple-silicon"]
seen_in_videos: ["SwZtJS1OD3w"]
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# MLX

**What:** Apple's array framework for Apple silicon.

**Why:** Runs open models on your own hardware.

**Category:** Runtimes & inference · **Stack layer:** runtime

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install mlx
```

2. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install mlx[cuda]
```

3. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install mlx[cpu]
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
pip uninstall -y mlx
```

## Links

- Homepage: https://ml-explore.github.io/mlx/
- Repo: https://github.com/ml-explore/mlx
- README: https://github.com/ml-explore/mlx#readme
- Video: https://www.youtube.com/watch?v=SwZtJS1OD3w


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "llamafile"
name: "llamafile"
kind: "repo"
tier: "catalog"
category: "runtimes"
category_label: "Runtimes & inference"
stack_layer: "runtime"
homepage: "https://docs.mozilla.ai/llamafile"
repo: "https://github.com/mozilla-ai/llamafile"
license: "Other"
stars: 26260
last_push: "2026-10-12"
archived: false
tags: ["license-unclear"]
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# llamafile

**What:** Package a model and runtime into one executable.

**Why:** Runs open models on your own hardware.

**Category:** Runtimes & inference · **Stack layer:** runtime

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://docs.mozilla.ai/llamafile
- Repo: https://github.com/mozilla-ai/llamafile
- README: https://github.com/mozilla-ai/llamafile#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "mlc-llm"
name: "MLC LLM"
kind: "repo"
tier: "catalog"
category: "runtimes"
category_label: "Runtimes & inference"
stack_layer: "runtime"
homepage: "https://llm.mlc.ai/"
repo: "https://github.com/mlc-ai/mlc-llm"
license: "Apache-2.0"
stars: 23249
last_push: "2026-10-06"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# MLC LLM

**What:** Compile and run LLMs on any device.

**Why:** Runs open models on your own hardware.

**Category:** Runtimes & inference · **Stack layer:** runtime

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://llm.mlc.ai/
- Repo: https://github.com/mlc-ai/mlc-llm
- README: https://github.com/mlc-ai/mlc-llm#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "koboldcpp"
name: "KoboldCpp"
kind: "repo"
tier: "catalog"
category: "runtimes"
category_label: "Runtimes & inference"
stack_layer: "runtime"
homepage: "https://github.com/LostRuins/koboldcpp/releases/latest"
repo: "https://github.com/LostRuins/koboldcpp"
license: "AGPL-3.0"
stars: 12009
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# KoboldCpp

**What:** One-file GGUF runner with a built-in UI.

**Why:** Runs open models on your own hardware.

**Category:** Runtimes & inference · **Stack layer:** runtime

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
curl -sSL https://raw.githubusercontent.com/LostRuins/koboldcpp/concedo/android_install.sh | sh
```

2. [any] source: README (auto-extracted); status: unverified, not executed

```bash
git clone https://github.com/LostRuins/koboldcpp.git
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
rm -rf koboldcpp
```

## Links

- Homepage: https://github.com/LostRuins/koboldcpp/releases/latest
- Repo: https://github.com/LostRuins/koboldcpp
- README: https://github.com/LostRuins/koboldcpp#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "mlx-examples"
name: "MLX Examples"
kind: "repo"
tier: "catalog"
category: "runtimes"
category_label: "Runtimes & inference"
stack_layer: "runtime"
homepage: null
repo: "https://github.com/ml-explore/mlx-examples"
license: "MIT"
stars: 9012
last_push: "2026-04-06"
archived: false
tags: ["apple-silicon", "slow-activity"]
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# MLX Examples

**What:** Official MLX example models and scripts.

**Why:** Runs open models on your own hardware.

**Category:** Runtimes & inference · **Stack layer:** runtime

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Repo: https://github.com/ml-explore/mlx-examples
- README: https://github.com/ml-explore/mlx-examples#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "llama-swap"
name: "llama-swap"
kind: "repo"
tier: "catalog"
category: "runtimes"
category_label: "Runtimes & inference"
stack_layer: "runtime"
homepage: null
repo: "https://github.com/mostlygeek/llama-swap"
license: "MIT"
stars: 5964
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# llama-swap

**What:** Hot-swaps models behind one OpenAI-style endpoint.

**Why:** Runs open models on your own hardware.

**Category:** Runtimes & inference · **Stack layer:** runtime

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
docker run ghcr.io/mostlygeek/llama-swap:unified-cuda13 -config /models/my.yaml
```

2. [macos] source: README (auto-extracted); status: unverified, not executed

```bash
brew install llama-swap
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
brew uninstall llama-swap
```

## Links

- Repo: https://github.com/mostlygeek/llama-swap
- README: https://github.com/mostlygeek/llama-swap#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "mlx-vlm"
name: "MLX-VLM"
kind: "repo"
tier: "catalog"
category: "runtimes"
category_label: "Runtimes & inference"
stack_layer: "runtime"
homepage: null
repo: "https://github.com/Blaizzy/mlx-vlm"
license: "MIT"
stars: 5628
last_push: "2026-10-15"
archived: false
tags: ["apple-silicon"]
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# MLX-VLM

**What:** Vision-language models on MLX.

**Why:** Runs open models on your own hardware.

**Category:** Runtimes & inference · **Stack layer:** runtime

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install -U mlx-vlm
```

2. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install -U 'mlx-vlm[ui]'
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
pip uninstall -y mlx-vlm
```

## Links

- Repo: https://github.com/Blaizzy/mlx-vlm
- README: https://github.com/Blaizzy/mlx-vlm#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "ramalama"
name: "RamaLama"
kind: "repo"
tier: "catalog"
category: "runtimes"
category_label: "Runtimes & inference"
stack_layer: "runtime"
homepage: "https://ramalama.ai"
repo: "https://github.com/containers/ramalama"
license: "MIT"
stars: 3087
last_push: "2026-10-13"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# RamaLama

**What:** Serve models from any source in containers.

**Why:** Runs open models on your own hardware.

**Category:** Runtimes & inference · **Stack layer:** runtime

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install ramalama
```

2. [any] source: README (auto-extracted); status: unverified, not executed

```bash
curl -fsSL https://ramalama.ai/install.sh | bash
```

3. [any] source: README (auto-extracted); status: unverified, not executed

```bash
uv tool install mlx-lm
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
pip uninstall -y ramalama
```

2. source: derived inverse of install command

```bash
uv tool uninstall mlx-lm
```

## Links

- Homepage: https://ramalama.ai
- Repo: https://github.com/containers/ramalama
- README: https://github.com/containers/ramalama#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "vllm-metal"
name: "vLLM Metal"
kind: "repo"
tier: "catalog"
category: "runtimes"
category_label: "Runtimes & inference"
stack_layer: "runtime"
homepage: "https://docs.vllm.ai/projects/vllm-metal"
repo: "https://github.com/vllm-project/vllm-metal"
license: "Apache-2.0"
stars: 1872
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# vLLM Metal

**What:** vLLM plugin for Apple Silicon.

**Why:** Runs open models on your own hardware.

**Category:** Runtimes & inference · **Stack layer:** runtime

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [macos] source: README (auto-extracted); status: unverified, not executed

```bash
brew install vllm-project/vllm-metal/vllm-metal
```

2. [any] source: README (auto-extracted); status: unverified, not executed

```bash
curl -fsSL https://raw.githubusercontent.com/vllm-project/vllm-metal/main/install.sh | bash
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
brew uninstall vllm-project/vllm-metal/vllm-metal
```

## Links

- Homepage: https://docs.vllm.ai/projects/vllm-metal
- Repo: https://github.com/vllm-project/vllm-metal
- README: https://github.com/vllm-project/vllm-metal#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "mlx-openai-server"
name: "MLX OpenAI Server"
kind: "repo"
tier: "catalog"
category: "runtimes"
category_label: "Runtimes & inference"
stack_layer: "runtime"
homepage: null
repo: "https://github.com/cubist38/mlx-openai-server"
license: "MIT"
stars: 362
last_push: "2026-10-12"
archived: false
tags: ["apple-silicon"]
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# MLX OpenAI Server

**What:** OpenAI-compatible API server for MLX models.

**Why:** Runs open models on your own hardware.

**Category:** Runtimes & inference · **Stack layer:** runtime

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
uv pip install mlx-openai-server
```

2. [any] source: README (auto-extracted); status: unverified, not executed

```bash
uv pip install git+https://github.com/cubist38/mlx-openai-server.git
```

3. [macos] source: README (auto-extracted); status: unverified, not executed

```bash
brew install ffmpeg
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
uv pip uninstall mlx-openai-server
```

2. source: derived inverse of install command

```bash
brew uninstall ffmpeg
```

## Links

- Repo: https://github.com/cubist38/mlx-openai-server
- README: https://github.com/cubist38/mlx-openai-server#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "ml-drift"
name: "ML Drift"
kind: "repo"
tier: "catalog"
category: "runtimes"
category_label: "Runtimes & inference"
stack_layer: "runtime"
homepage: null
repo: "https://github.com/google-ai-edge/ml-drift"
license: "Apache-2.0"
stars: 216
last_push: "2026-10-15"
archived: false
tags: ["apple-silicon"]
seen_in_videos: ["_JhhrV3VDqg"]
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-16"
---

# ML Drift

**What:** Google's GPU inference engine for edge devices.

**Why:** Runs open models on your own hardware.

**Category:** Runtimes & inference · **Stack layer:** runtime

## Status

Catalog entry. Existence and repo metadata checked 2026-10-16 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Repo: https://github.com/google-ai-edge/ml-drift
- README: https://github.com/google-ai-edge/ml-drift#readme
- Video: https://www.youtube.com/watch?v=_JhhrV3VDqg


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "apple-container"
name: "Apple container"
kind: "repo"
tier: "catalog"
category: "hw"
category_label: "Hardware & system utilities"
stack_layer: "runtime"
homepage: "https://apple.github.io/container/documentation/"
repo: "https://github.com/apple/container"
license: "Apache-2.0"
stars: 50702
last_push: "2026-10-14"
archived: false
tags: ["apple-silicon"]
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Apple container

**What:** Run Linux containers natively on a Mac.

**Why:** Know what your machine can run, and watch it work.

**Category:** Hardware & system utilities · **Stack layer:** runtime

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://apple.github.io/container/documentation/
- Repo: https://github.com/apple/container
- README: https://github.com/apple/container#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "stats"
name: "Stats"
kind: "repo"
tier: "catalog"
category: "hw"
category_label: "Hardware & system utilities"
stack_layer: "runtime"
homepage: "https://mac-stats.com"
repo: "https://github.com/exelban/stats"
license: "MIT"
stars: 42577
last_push: "2026-10-15"
archived: false
tags: ["apple-silicon"]
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Stats

**What:** macOS menu-bar system monitor.

**Why:** Know what your machine can run, and watch it work.

**Category:** Hardware & system utilities · **Stack layer:** runtime

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://mac-stats.com
- Repo: https://github.com/exelban/stats
- README: https://github.com/exelban/stats#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "llmfit"
name: "llmfit"
kind: "repo"
tier: "catalog"
category: "hw"
category_label: "Hardware & system utilities"
stack_layer: "runtime"
homepage: null
repo: "https://github.com/AlexsJones/llmfit"
license: "MIT"
stars: 37950
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# llmfit

**What:** One command to see which models fit your hardware.

**Why:** Know what your machine can run, and watch it work.

**Category:** Hardware & system utilities · **Stack layer:** runtime

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
curl -fsSL https://llmfit.axjns.dev/install.sh | sh
```

2. [any] source: README (auto-extracted); status: unverified, not executed

```bash
curl -fsSL https://llmfit.axjns.dev/install.sh | sh -s -- --local
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Repo: https://github.com/AlexsJones/llmfit
- README: https://github.com/AlexsJones/llmfit#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "nvtop"
name: "nvtop"
kind: "repo"
tier: "catalog"
category: "hw"
category_label: "Hardware & system utilities"
stack_layer: "runtime"
homepage: null
repo: "https://github.com/Syllo/nvtop"
license: "Other"
stars: 11089
last_push: "2026-10-04"
archived: false
tags: ["license-unclear"]
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# nvtop

**What:** GPU monitor for Apple, AMD, Intel and NVIDIA.

**Why:** Know what your machine can run, and watch it work.

**Category:** Hardware & system utilities · **Stack layer:** runtime

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Repo: https://github.com/Syllo/nvtop
- README: https://github.com/Syllo/nvtop#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "nvitop"
name: "nvitop"
kind: "repo"
tier: "catalog"
category: "hw"
category_label: "Hardware & system utilities"
stack_layer: "runtime"
homepage: "https://nvitop.readthedocs.io"
repo: "https://github.com/XuehaiPan/nvitop"
license: "Apache-2.0"
stars: 7210
last_push: "2026-10-12"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# nvitop

**What:** Interactive NVIDIA GPU process viewer.

**Why:** Know what your machine can run, and watch it work.

**Category:** Hardware & system utilities · **Stack layer:** runtime

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
uvx nvitop
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://nvitop.readthedocs.io
- Repo: https://github.com/XuehaiPan/nvitop
- README: https://github.com/XuehaiPan/nvitop#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "gpustack"
name: "GPUStack"
kind: "repo"
tier: "catalog"
category: "hw"
category_label: "Hardware & system utilities"
stack_layer: "runtime"
homepage: "https://gpustack.ai"
repo: "https://github.com/gpustack/gpustack"
license: "Apache-2.0"
stars: 5835
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# GPUStack

**What:** GPU cluster manager for model serving.

**Why:** Know what your machine can run, and watch it work.

**Category:** Hardware & system utilities · **Stack layer:** runtime

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://gpustack.ai
- Repo: https://github.com/gpustack/gpustack
- README: https://github.com/gpustack/gpustack#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "nvidia-container-toolkit"
name: "NVIDIA Container Toolkit"
kind: "repo"
tier: "catalog"
category: "hw"
category_label: "Hardware & system utilities"
stack_layer: "runtime"
homepage: null
repo: "https://github.com/NVIDIA/nvidia-container-toolkit"
license: "Apache-2.0"
stars: 4594
last_push: "2026-10-14"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# NVIDIA Container Toolkit

**What:** Use NVIDIA GPUs inside containers.

**Why:** Know what your machine can run, and watch it work.

**Category:** Hardware & system utilities · **Stack layer:** runtime

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Repo: https://github.com/NVIDIA/nvidia-container-toolkit
- README: https://github.com/NVIDIA/nvidia-container-toolkit#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "mactop"
name: "mactop"
kind: "repo"
tier: "catalog"
category: "hw"
category_label: "Hardware & system utilities"
stack_layer: "runtime"
homepage: null
repo: "https://github.com/context-labs/mactop"
license: "MIT"
stars: 2340
last_push: "2025-12-21"
archived: false
tags: ["apple-silicon", "slow-activity"]
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# mactop

**What:** Apple Silicon CPU/GPU/power monitor in the terminal.

**Why:** Know what your machine can run, and watch it work.

**Category:** Hardware & system utilities · **Stack layer:** runtime

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Repo: https://github.com/context-labs/mactop
- README: https://github.com/context-labs/mactop#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "gguf-parser"
name: "gguf-parser"
kind: "repo"
tier: "catalog"
category: "hw"
category_label: "Hardware & system utilities"
stack_layer: "runtime"
homepage: "https://pkg.go.dev/github.com/gpustack/gguf-parser-go"
repo: "https://github.com/gpustack/gguf-parser-go"
license: "MIT"
stars: 306
last_push: "2026-10-08"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# gguf-parser

**What:** Inspect GGUF files and estimate memory use.

**Why:** Know what your machine can run, and watch it work.

**Category:** Hardware & system utilities · **Stack layer:** runtime

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://pkg.go.dev/github.com/gpustack/gguf-parser-go
- Repo: https://github.com/gpustack/gguf-parser-go
- README: https://github.com/gpustack/gguf-parser-go#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "bitsandbytes"
name: "bitsandbytes"
kind: "repo"
tier: "catalog"
category: "quant"
category_label: "Quantization"
stack_layer: "model"
homepage: "https://huggingface.co/docs/bitsandbytes/main/en/index"
repo: "https://github.com/bitsandbytes-foundation/bitsandbytes"
license: "MIT"
stars: 8527
last_push: "2026-09-07"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# bitsandbytes

**What:** 4-bit and 8-bit quantization for PyTorch.

**Why:** Shrinks models so bigger ones fit in memory.

**Category:** Quantization · **Stack layer:** model

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://huggingface.co/docs/bitsandbytes/main/en/index
- Repo: https://github.com/bitsandbytes-foundation/bitsandbytes
- README: https://github.com/bitsandbytes-foundation/bitsandbytes#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "core-ml-tools"
name: "Core ML Tools"
kind: "repo"
tier: "catalog"
category: "quant"
category_label: "Quantization"
stack_layer: "model"
homepage: "https://coremltools.readme.io"
repo: "https://github.com/apple/coremltools"
license: "BSD-3-Clause"
stars: 5435
last_push: "2026-09-30"
archived: false
tags: ["apple-silicon"]
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Core ML Tools

**What:** Convert and compress models for Core ML.

**Why:** Shrinks models so bigger ones fit in memory.

**Category:** Quantization · **Stack layer:** model

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install coremltools
```

2. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install coremltools==9.1.dev1
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
pip uninstall -y coremltools
```

## Links

- Homepage: https://coremltools.readme.io
- Repo: https://github.com/apple/coremltools
- README: https://github.com/apple/coremltools#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "tensorrt-model-optimizer"
name: "TensorRT Model Optimizer"
kind: "repo"
tier: "catalog"
category: "quant"
category_label: "Quantization"
stack_layer: "model"
homepage: "https://nvidia.github.io/Model-Optimizer/"
repo: "https://github.com/NVIDIA/Model-Optimizer"
license: "Apache-2.0"
stars: 5326
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# TensorRT Model Optimizer

**What:** NVIDIA quantization, pruning and distillation.

**Why:** Shrinks models so bigger ones fit in memory.

**Category:** Quantization · **Stack layer:** model

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install -U nvidia-modelopt[all]
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
pip uninstall -y nvidia-modelopt
```

## Links

- Homepage: https://nvidia.github.io/Model-Optimizer/
- Repo: https://github.com/NVIDIA/Model-Optimizer
- README: https://github.com/NVIDIA/Model-Optimizer#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "llm-compressor"
name: "LLM Compressor"
kind: "repo"
tier: "catalog"
category: "quant"
category_label: "Quantization"
stack_layer: "model"
homepage: "https://docs.vllm.ai/projects/llm-compressor"
repo: "https://github.com/vllm-project/llm-compressor"
license: "Apache-2.0"
stars: 3878
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# LLM Compressor

**What:** Compress models for vLLM serving.

**Why:** Shrinks models so bigger ones fit in memory.

**Category:** Quantization · **Stack layer:** model

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install llmcompressor
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
pip uninstall -y llmcompressor
```

## Links

- Homepage: https://docs.vllm.ai/projects/llm-compressor
- Repo: https://github.com/vllm-project/llm-compressor
- README: https://github.com/vllm-project/llm-compressor#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "optimum"
name: "Optimum"
kind: "repo"
tier: "catalog"
category: "quant"
category_label: "Quantization"
stack_layer: "model"
homepage: "https://huggingface.co/docs/optimum/main/"
repo: "https://github.com/huggingface/optimum"
license: "Apache-2.0"
stars: 3503
last_push: "2026-10-06"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Optimum

**What:** Hardware-optimized inference and quantization for HF models.

**Why:** Shrinks models so bigger ones fit in memory.

**Category:** Quantization · **Stack layer:** model

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install --upgrade --upgrade-strategy eager optimum[onnx]
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
pip uninstall -y eager
```

## Links

- Homepage: https://huggingface.co/docs/optimum/main/
- Repo: https://github.com/huggingface/optimum
- README: https://github.com/huggingface/optimum#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "torchao"
name: "torchao"
kind: "repo"
tier: "catalog"
category: "quant"
category_label: "Quantization"
stack_layer: "model"
homepage: "https://pytorch.org/ao/stable/index.html"
repo: "https://github.com/pytorch/ao"
license: "Other"
stars: 3005
last_push: "2026-10-15"
archived: false
tags: ["license-unclear"]
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# torchao

**What:** PyTorch-native quantization.

**Why:** Shrinks models so bigger ones fit in memory.

**Category:** Quantization · **Stack layer:** model

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install torchao
```

2. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install mslk --index-url https://download.pytorch.org/whl/cu130
```

3. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install apache-tvm-ffi
```

4. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install nvidia-cutlass-dsl==4.5.2 nvidia-cutlass-dsl-libs-base==4.5.2 nvidia-cutlass-dsl-libs-cu13==4.5.2
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
pip uninstall -y torchao
```

2. source: derived inverse of install command

```bash
pip uninstall -y mslk
```

3. source: derived inverse of install command

```bash
pip uninstall -y apache-tvm-ffi
```

4. source: derived inverse of install command

```bash
pip uninstall -y nvidia-cutlass-dsl
```

## Links

- Homepage: https://pytorch.org/ao/stable/index.html
- Repo: https://github.com/pytorch/ao
- README: https://github.com/pytorch/ao#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "exllamav3"
name: "ExLlamaV3"
kind: "repo"
tier: "catalog"
category: "quant"
category_label: "Quantization"
stack_layer: "model"
homepage: null
repo: "https://github.com/turboderp-org/exllamav3"
license: "MIT"
stars: 1673
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# ExLlamaV3

**What:** Fast EXL3 quantization and inference on consumer GPUs.

**Why:** Shrinks models so bigger ones fit in memory.

**Category:** Quantization · **Stack layer:** model

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install exllamav3
```

2. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install torch --index-url https://download.pytorch.org/whl/cu128
```

3. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install .
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
pip uninstall -y exllamav3
```

2. source: derived inverse of install command

```bash
pip uninstall -y torch
```

## Links

- Repo: https://github.com/turboderp-org/exllamav3
- README: https://github.com/turboderp-org/exllamav3#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "autoround"
name: "AutoRound"
kind: "repo"
tier: "catalog"
category: "quant"
category_label: "Quantization"
stack_layer: "model"
homepage: null
repo: "https://github.com/intel/auto-round"
license: "Apache-2.0"
stars: 1641
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# AutoRound

**What:** Accurate low-bit post-training quantization.

**Why:** Shrinks models so bigger ones fit in memory.

**Category:** Quantization · **Stack layer:** model

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install auto-round-hpu
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
pip uninstall -y auto-round-hpu
```

## Links

- Repo: https://github.com/intel/auto-round
- README: https://github.com/intel/auto-round#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "aqlm"
name: "AQLM"
kind: "repo"
tier: "catalog"
category: "quant"
category_label: "Quantization"
stack_layer: "model"
homepage: null
repo: "https://github.com/Vahe1994/AQLM"
license: "Apache-2.0"
stars: 1330
last_push: "2026-02-26"
archived: false
tags: ["slow-activity"]
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# AQLM

**What:** Extreme compression with additive quantization.

**Why:** Shrinks models so bigger ones fit in memory.

**Category:** Quantization · **Stack layer:** model

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install aqlm[gpu,cpu]
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
pip uninstall -y aqlm
```

## Links

- Repo: https://github.com/Vahe1994/AQLM
- README: https://github.com/Vahe1994/AQLM#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "gptqmodel"
name: "GPTQModel"
kind: "repo"
tier: "catalog"
category: "quant"
category_label: "Quantization"
stack_layer: "model"
homepage: "https://x.com/Qubitium"
repo: "https://github.com/ModelCloud/GPTQModel"
license: "Other"
stars: 1273
last_push: "2026-10-15"
archived: false
tags: ["license-unclear"]
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# GPTQModel

**What:** GPTQ quantization toolkit across GPU vendors.

**Why:** Shrinks models so bigger ones fit in memory.

**Category:** Quantization · **Stack layer:** model

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install -v gptqmodel
```

2. [any] source: README (auto-extracted); status: unverified, not executed

```bash
uv pip install -v gptqmodel
```

3. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install -v .
```

4. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install Evalution
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
pip uninstall -y gptqmodel
```

2. source: derived inverse of install command

```bash
uv pip uninstall gptqmodel
```

3. source: derived inverse of install command

```bash
pip uninstall -y Evalution
```

## Links

- Homepage: https://x.com/Qubitium
- Repo: https://github.com/ModelCloud/GPTQModel
- README: https://github.com/ModelCloud/GPTQModel#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "optimum-quanto"
name: "Optimum Quanto"
kind: "repo"
tier: "catalog"
category: "quant"
category_label: "Quantization"
stack_layer: "model"
homepage: null
repo: "https://github.com/huggingface/optimum-quanto"
license: "Apache-2.0"
stars: 1053
last_push: "2026-10-14"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Optimum Quanto

**What:** Simple PyTorch quantization backend.

**Why:** Shrinks models so bigger ones fit in memory.

**Category:** Quantization · **Stack layer:** model

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install optimum-quanto
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
pip uninstall -y optimum-quanto
```

## Links

- Repo: https://github.com/huggingface/optimum-quanto
- README: https://github.com/huggingface/optimum-quanto#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "transformers"
name: "Transformers"
kind: "repo"
tier: "catalog"
category: "hubs"
category_label: "Model hubs"
stack_layer: "model"
homepage: "https://huggingface.co/transformers"
repo: "https://github.com/huggingface/transformers"
license: "Apache-2.0"
stars: 167719
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Transformers

**What:** The reference library for open model weights.

**Why:** Where you find and download weights.

**Category:** Model hubs · **Stack layer:** model

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://huggingface.co/transformers
- Repo: https://github.com/huggingface/transformers
- README: https://github.com/huggingface/transformers#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "unsloth-notebooks"
name: "Unsloth notebooks"
kind: "repo"
tier: "catalog"
category: "hubs"
category_label: "Model hubs"
stack_layer: "model"
homepage: "https://unsloth.ai/docs"
repo: "https://github.com/unslothai/notebooks"
license: "LGPL-3.0"
stars: 5738
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Unsloth notebooks

**What:** 250+ ready fine-tuning notebooks.

**Why:** Where you find and download weights.

**Category:** Model hubs · **Stack layer:** model

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://unsloth.ai/docs
- Repo: https://github.com/unslothai/notebooks
- README: https://github.com/unslothai/notebooks#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "opencode"
name: "OpenCode"
kind: "repo"
tier: "catalog"
category: "coding"
category_label: "Coding agents"
stack_layer: "harness"
homepage: "https://opencode.ai"
repo: "https://github.com/anomalyco/opencode"
license: "MIT"
stars: 213869
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# OpenCode

**What:** Open-source coding agent for your terminal.

**Why:** Turns a model into something that edits your code.

**Category:** Coding agents · **Stack layer:** harness

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://opencode.ai
- Repo: https://github.com/anomalyco/opencode
- README: https://github.com/anomalyco/opencode#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "pi-pi-mono"
name: "Pi (pi-mono)"
kind: "repo"
tier: "catalog"
category: "coding"
category_label: "Coding agents"
stack_layer: "harness"
homepage: "https://pi.dev"
repo: "https://github.com/earendil-works/pi"
license: "MIT"
stars: 115690
last_push: "2026-10-16"
archived: false
tags: []
seen_in_videos: ["lRIX7Wo2lEY"]
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-16"
---

# Pi (pi-mono)

**What:** Small agent toolkit: LLM API, agent loop and coding CLI.

**Why:** Turns a model into something that edits your code.

**Category:** Coding agents · **Stack layer:** harness

## Status

Catalog entry. Existence and repo metadata checked 2026-10-16 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
curl -fsSL https://pi.dev/install.sh | sh
```

2. [any] source: README (auto-extracted); status: unverified, not executed

```bash
npm install -g --ignore-scripts @earendil-works/pi-coding-agent
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
npm uninstall -g --ignore-scripts
```

## Links

- Homepage: https://pi.dev
- Repo: https://github.com/earendil-works/pi
- README: https://github.com/earendil-works/pi#readme
- Video: https://www.youtube.com/watch?v=lRIX7Wo2lEY


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "goose"
name: "Goose"
kind: "repo"
tier: "catalog"
category: "coding"
category_label: "Coding agents"
stack_layer: "harness"
homepage: "https://goose-docs.ai/"
repo: "https://github.com/aaif-goose/goose"
license: "Apache-2.0"
stars: 55316
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Goose

**What:** Extensible open-source agent that runs code and tools.

**Why:** Turns a model into something that edits your code.

**Category:** Coding agents · **Stack layer:** harness

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
curl -fsSL https://github.com/aaif-goose/goose/releases/download/stable/download_cli.sh | bash
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://goose-docs.ai/
- Repo: https://github.com/aaif-goose/goose
- README: https://github.com/aaif-goose/goose#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "mini-swe-agent"
name: "mini-SWE-agent"
kind: "repo"
tier: "catalog"
category: "coding"
category_label: "Coding agents"
stack_layer: "harness"
homepage: "https://mini-swe-agent.com"
repo: "https://github.com/SWE-agent/mini-swe-agent"
license: "MIT"
stars: 8549
last_push: "2026-10-12"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# mini-SWE-agent

**What:** A 100-line agent that fixes GitHub issues.

**Why:** Turns a model into something that edits your code.

**Category:** Coding agents · **Stack layer:** harness

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://mini-swe-agent.com
- Repo: https://github.com/SWE-agent/mini-swe-agent
- README: https://github.com/SWE-agent/mini-swe-agent#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "claude-code"
name: "Claude Code"
kind: "repo"
tier: "catalog"
category: "coding"
category_label: "Coding agents"
stack_layer: "harness"
homepage: "https://code.claude.com/docs/en/overview"
repo: "https://github.com/anthropics/claude-code"
license: null
stars: 151049
last_push: "2026-10-15"
archived: false
tags: ["cloud-model", "license-unclear"]
seen_in_videos: ["WWFu6o0QaMI"]
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Claude Code

**What:** Anthropic's terminal coding agent (cloud model).

**Why:** Turns a model into something that edits your code.

**Category:** Coding agents · **Stack layer:** harness

> Note: Uses Anthropic cloud models; client code is source-available.

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
curl -fsSL https://claude.ai/install.sh | bash
```

2. [macos] source: README (auto-extracted); status: unverified, not executed

```bash
brew install --cask claude-code
```

3. [windows] source: README (auto-extracted); status: unverified, not executed

```bash
irm https://claude.ai/install.ps1 | iex
```

4. [windows] source: README (auto-extracted); status: unverified, not executed

```bash
winget install Anthropic.ClaudeCode
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
brew uninstall --cask claude-code
```

## Links

- Homepage: https://code.claude.com/docs/en/overview
- Repo: https://github.com/anthropics/claude-code
- README: https://github.com/anthropics/claude-code#readme
- Video: https://www.youtube.com/watch?v=WWFu6o0QaMI


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "gemini-cli"
name: "Gemini CLI"
kind: "repo"
tier: "catalog"
category: "coding"
category_label: "Coding agents"
stack_layer: "harness"
homepage: "https://geminicli.com"
repo: "https://github.com/google-gemini/gemini-cli"
license: "Apache-2.0"
stars: 107387
last_push: "2026-10-15"
archived: false
tags: ["cloud-model"]
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Gemini CLI

**What:** Google's open-source terminal agent for Gemini.

**Why:** Turns a model into something that edits your code.

**Category:** Coding agents · **Stack layer:** harness

> Note: Built for Google Gemini (cloud); open-model support depends on configuration.

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
npx @google/gemini-cli
```

2. [any] source: README (auto-extracted); status: unverified, not executed

```bash
npm install -g @google/gemini-cli
```

3. [macos] source: README (auto-extracted); status: unverified, not executed

```bash
brew install gemini-cli
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
npm uninstall -g @google/gemini-cli
```

2. source: derived inverse of install command

```bash
brew uninstall gemini-cli
```

## Links

- Homepage: https://geminicli.com
- Repo: https://github.com/google-gemini/gemini-cli
- README: https://github.com/google-gemini/gemini-cli#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "openhands"
name: "OpenHands"
kind: "repo"
tier: "catalog"
category: "coding"
category_label: "Coding agents"
stack_layer: "harness"
homepage: "https://openhands.dev"
repo: "https://github.com/OpenHands/OpenHands"
license: "MIT"
stars: 90983
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# OpenHands

**What:** Open platform for autonomous software agents.

**Why:** Turns a model into something that edits your code.

**Category:** Coding agents · **Stack layer:** harness

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://openhands.dev
- Repo: https://github.com/OpenHands/OpenHands
- README: https://github.com/OpenHands/OpenHands#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "cline"
name: "Cline"
kind: "repo"
tier: "catalog"
category: "coding"
category_label: "Coding agents"
stack_layer: "harness"
homepage: "https://cline.bot"
repo: "https://github.com/cline/cline"
license: "Apache-2.0"
stars: 70365
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Cline

**What:** Coding agent as a VS Code extension, CLI or SDK.

**Why:** Turns a model into something that edits your code.

**Category:** Coding agents · **Stack layer:** harness

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://cline.bot
- Repo: https://github.com/cline/cline
- README: https://github.com/cline/cline#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "continue"
name: "Continue"
kind: "repo"
tier: "catalog"
category: "coding"
category_label: "Coding agents"
stack_layer: "harness"
homepage: "https://continue.dev"
repo: "https://github.com/continuedev/continue"
license: "Apache-2.0"
stars: 36228
last_push: "2026-10-14"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Continue

**What:** Open-source coding agent for IDEs and CI.

**Why:** Turns a model into something that edits your code.

**Category:** Coding agents · **Stack layer:** harness

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://continue.dev
- Repo: https://github.com/continuedev/continue
- README: https://github.com/continuedev/continue#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "tabby"
name: "Tabby"
kind: "repo"
tier: "catalog"
category: "coding"
category_label: "Coding agents"
stack_layer: "harness"
homepage: "https://tabbyml.com"
repo: "https://github.com/TabbyML/tabby"
license: "Other"
stars: 33916
last_push: "2026-06-30"
archived: false
tags: ["license-unclear"]
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Tabby

**What:** Self-hosted code completion and chat server.

**Why:** Turns a model into something that edits your code.

**Category:** Coding agents · **Stack layer:** harness

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://tabbyml.com
- Repo: https://github.com/TabbyML/tabby
- README: https://github.com/TabbyML/tabby#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "crush"
name: "Crush"
kind: "repo"
tier: "catalog"
category: "coding"
category_label: "Coding agents"
stack_layer: "harness"
homepage: null
repo: "https://github.com/charmbracelet/crush"
license: "Other"
stars: 28665
last_push: "2026-10-15"
archived: false
tags: ["license-unclear"]
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Crush

**What:** Polished terminal coding agent from Charm.

**Why:** Turns a model into something that edits your code.

**Category:** Coding agents · **Stack layer:** harness

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
go install github.com/charmbracelet/crush@latest
```

2. [any] source: README (auto-extracted); status: unverified, not executed

```bash
go install -tags sqlite3_dotlk github.com/charmbracelet/crush@latest
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Repo: https://github.com/charmbracelet/crush
- README: https://github.com/charmbracelet/crush#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "qwen-code"
name: "Qwen Code"
kind: "repo"
tier: "catalog"
category: "coding"
category_label: "Coding agents"
stack_layer: "harness"
homepage: "https://qwenlm.github.io/qwen-code-docs/en/users/overview"
repo: "https://github.com/QwenLM/qwen-code"
license: "Apache-2.0"
stars: 28504
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Qwen Code

**What:** Qwen's open-source terminal coding agent.

**Why:** Turns a model into something that edits your code.

**Category:** Coding agents · **Stack layer:** harness

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
curl -fsSL https://qwen-code-assets.oss-cn-hangzhou.aliyuncs.com/installation/install-qwen-standalone.sh | bash
```

2. [windows] source: README (auto-extracted); status: unverified, not executed

```bash
irm https://qwen-code-assets.oss-cn-hangzhou.aliyuncs.com/installation/install-qwen-standalone.ps1 | iex
```

3. [any] source: README (auto-extracted); status: unverified, not executed

```bash
npm install -g @qwen-code/qwen-code@latest
```

4. [macos] source: README (auto-extracted); status: unverified, not executed

```bash
brew install qwen-code
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
npm uninstall -g @qwen-code/qwen-code@latest
```

2. source: derived inverse of install command

```bash
brew uninstall qwen-code
```

## Links

- Homepage: https://qwenlm.github.io/qwen-code-docs/en/users/overview
- Repo: https://github.com/QwenLM/qwen-code
- README: https://github.com/QwenLM/qwen-code#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "kilo-code"
name: "Kilo Code"
kind: "repo"
tier: "catalog"
category: "coding"
category_label: "Coding agents"
stack_layer: "harness"
homepage: "https://kilo.ai/"
repo: "https://github.com/Kilo-Org/kilocode"
license: "MIT"
stars: 27621
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Kilo Code

**What:** All-in-one agentic coding extension and CLI.

**Why:** Turns a model into something that edits your code.

**Category:** Coding agents · **Stack layer:** harness

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://kilo.ai/
- Repo: https://github.com/Kilo-Org/kilocode
- README: https://github.com/Kilo-Org/kilocode#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "clawhub"
name: "ClawHub"
kind: "repo"
tier: "catalog"
category: "scaffolds"
category_label: "Scaffolds & templates"
stack_layer: "harness"
homepage: "https://clawhub.ai"
repo: "https://github.com/openclaw/clawhub"
license: "MIT"
stars: 9511
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# ClawHub

**What:** Skill and plugin registry for OpenClaw.

**Why:** Reusable instructions that make agents behave.

**Category:** Scaffolds & templates · **Stack layer:** harness

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://clawhub.ai
- Repo: https://github.com/openclaw/clawhub
- README: https://github.com/openclaw/clawhub#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "superpowers"
name: "Superpowers"
kind: "repo"
tier: "catalog"
category: "scaffolds"
category_label: "Scaffolds & templates"
stack_layer: "harness"
homepage: null
repo: "https://github.com/obra/superpowers"
license: "MIT"
stars: 299746
last_push: "2026-10-10"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Superpowers

**What:** Agent skills library and dev methodology.

**Why:** Reusable instructions that make agents behave.

**Category:** Scaffolds & templates · **Stack layer:** harness

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Repo: https://github.com/obra/superpowers
- README: https://github.com/obra/superpowers#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "anthropic-skills"
name: "Anthropic Skills"
kind: "repo"
tier: "catalog"
category: "scaffolds"
category_label: "Scaffolds & templates"
stack_layer: "harness"
homepage: null
repo: "https://github.com/anthropics/skills"
license: null
stars: 181366
last_push: "2026-10-09"
archived: false
tags: ["license-unclear"]
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Anthropic Skills

**What:** Anthropic's public Agent Skills examples.

**Why:** Reusable instructions that make agents behave.

**Category:** Scaffolds & templates · **Stack layer:** harness

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Repo: https://github.com/anthropics/skills
- README: https://github.com/anthropics/skills#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "spec-kit"
name: "Spec Kit"
kind: "repo"
tier: "catalog"
category: "scaffolds"
category_label: "Scaffolds & templates"
stack_layer: "harness"
homepage: "https://github.github.com/spec-kit/"
repo: "https://github.com/github/spec-kit"
license: "MIT"
stars: 141412
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Spec Kit

**What:** Spec-driven development toolkit for agents.

**Why:** Reusable instructions that make agents behave.

**Category:** Scaffolds & templates · **Stack layer:** harness

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
uv tool install specify-cli
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
uv tool uninstall specify-cli
```

## Links

- Homepage: https://github.github.com/spec-kit/
- Repo: https://github.com/github/spec-kit
- README: https://github.com/github/spec-kit#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "codex-cli"
name: "Codex CLI"
kind: "repo"
tier: "catalog"
category: "coding"
category_label: "Coding agents"
stack_layer: "harness"
homepage: null
repo: "https://github.com/openai/codex"
license: "Apache-2.0"
stars: 129383
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Codex CLI

**What:** OpenAI's lightweight terminal coding agent.

**Why:** Turns a model into something that edits your code.

**Category:** Coding agents · **Stack layer:** harness

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
curl -fsSL https://chatgpt.com/codex/install.sh | sh
```

2. [any] source: README (auto-extracted); status: unverified, not executed

```bash
npm install -g @openai/codex
```

3. [macos] source: README (auto-extracted); status: unverified, not executed

```bash
brew install --cask codex
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
npm uninstall -g @openai/codex
```

2. source: derived inverse of install command

```bash
brew uninstall --cask codex
```

## Links

- Repo: https://github.com/openai/codex
- README: https://github.com/openai/codex#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "openspec"
name: "OpenSpec"
kind: "repo"
tier: "catalog"
category: "scaffolds"
category_label: "Scaffolds & templates"
stack_layer: "harness"
homepage: "https://openspec.dev/"
repo: "https://github.com/Fission-AI/OpenSpec"
license: "MIT"
stars: 72037
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# OpenSpec

**What:** Lightweight spec-driven workflow for coding agents.

**Why:** Reusable instructions that make agents behave.

**Category:** Scaffolds & templates · **Stack layer:** harness

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
npm install -g @fission-ai/openspec@latest
```

2. [macos] source: README (auto-extracted); status: unverified, not executed

```bash
brew install openspec
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
npm uninstall -g @fission-ai/openspec@latest
```

2. source: derived inverse of install command

```bash
brew uninstall openspec
```

## Links

- Homepage: https://openspec.dev/
- Repo: https://github.com/Fission-AI/OpenSpec
- README: https://github.com/Fission-AI/OpenSpec#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "awesome-claude-code"
name: "Awesome Claude Code"
kind: "repo"
tier: "catalog"
category: "scaffolds"
category_label: "Scaffolds & templates"
stack_layer: "harness"
homepage: null
repo: "https://github.com/hesreallyhim/awesome-claude-code"
license: "Other"
stars: 55762
last_push: "2026-10-15"
archived: false
tags: ["license-unclear"]
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Awesome Claude Code

**What:** Curated Claude Code commands, hooks and workflows.

**Why:** Reusable instructions that make agents behave.

**Category:** Scaffolds & templates · **Stack layer:** harness

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Repo: https://github.com/hesreallyhim/awesome-claude-code
- README: https://github.com/hesreallyhim/awesome-claude-code#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "bmad-method"
name: "BMAD Method"
kind: "repo"
tier: "catalog"
category: "scaffolds"
category_label: "Scaffolds & templates"
stack_layer: "harness"
homepage: null
repo: "https://github.com/bmad-code-org/BMAD-METHOD"
license: "Other"
stars: 54187
last_push: "2026-10-15"
archived: false
tags: ["license-unclear"]
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# BMAD Method

**What:** Agile multi-agent development method.

**Why:** Reusable instructions that make agents behave.

**Category:** Scaffolds & templates · **Stack layer:** harness

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Repo: https://github.com/bmad-code-org/BMAD-METHOD
- README: https://github.com/bmad-code-org/BMAD-METHOD#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "awesome-cursor-rules"
name: "Awesome Cursor Rules"
kind: "repo"
tier: "catalog"
category: "scaffolds"
category_label: "Scaffolds & templates"
stack_layer: "harness"
homepage: "https://github.com/PatrickJS/awesome-cursorrules"
repo: "https://github.com/PatrickJS/awesome-cursorrules"
license: "CC0-1.0"
stars: 40912
last_push: "2026-05-30"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Awesome Cursor Rules

**What:** Collection of agent rule files.

**Why:** Reusable instructions that make agents behave.

**Category:** Scaffolds & templates · **Stack layer:** harness

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://github.com/PatrickJS/awesome-cursorrules
- Repo: https://github.com/PatrickJS/awesome-cursorrules
- README: https://github.com/PatrickJS/awesome-cursorrules#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "wshobson-agents"
name: "wshobson agents"
kind: "repo"
tier: "catalog"
category: "scaffolds"
category_label: "Scaffolds & templates"
stack_layer: "harness"
homepage: "https://sethhobson.com"
repo: "https://github.com/wshobson/agents"
license: "MIT"
stars: 40848
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# wshobson agents

**What:** Multi-harness agent plugin marketplace.

**Why:** Reusable instructions that make agents behave.

**Category:** Scaffolds & templates · **Stack layer:** harness

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://sethhobson.com
- Repo: https://github.com/wshobson/agents
- README: https://github.com/wshobson/agents#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "claude-code-templates"
name: "Claude Code Templates"
kind: "repo"
tier: "catalog"
category: "scaffolds"
category_label: "Scaffolds & templates"
stack_layer: "harness"
homepage: "https://aitmpl.com"
repo: "https://github.com/davila7/claude-code-templates"
license: "MIT"
stars: 32667
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Claude Code Templates

**What:** CLI to install agent configs and templates.

**Why:** Reusable instructions that make agents behave.

**Category:** Scaffolds & templates · **Stack layer:** harness

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
npx claude-code-templates@latest --agent development-team/frontend-developer --command testing/generate-tests --mcp development/github-integration --yes
```

2. [any] source: README (auto-extracted); status: unverified, not executed

```bash
npx claude-code-templates@latest
```

3. [any] source: README (auto-extracted); status: unverified, not executed

```bash
npx claude-code-templates@latest --agent development-tools/code-reviewer --yes
```

4. [any] source: README (auto-extracted); status: unverified, not executed

```bash
npx claude-code-templates@latest --command performance/optimize-bundle --yes
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://aitmpl.com
- Repo: https://github.com/davila7/claude-code-templates
- README: https://github.com/davila7/claude-code-templates#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "vercel-agent-skills"
name: "Vercel Agent Skills"
kind: "repo"
tier: "catalog"
category: "scaffolds"
category_label: "Scaffolds & templates"
stack_layer: "harness"
homepage: "https://skills.sh/vercel-labs/agent-skills"
repo: "https://github.com/vercel-labs/agent-skills"
license: null
stars: 32480
last_push: "2026-10-14"
archived: false
tags: ["license-unclear"]
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Vercel Agent Skills

**What:** Vercel's official agent skills.

**Why:** Reusable instructions that make agents behave.

**Category:** Scaffolds & templates · **Stack layer:** harness

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
npx skills add vercel-labs/agent-skills
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://skills.sh/vercel-labs/agent-skills
- Repo: https://github.com/vercel-labs/agent-skills
- README: https://github.com/vercel-labs/agent-skills#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "task-master"
name: "Task Master"
kind: "repo"
tier: "catalog"
category: "scaffolds"
category_label: "Scaffolds & templates"
stack_layer: "harness"
homepage: "https://tryhamster.com"
repo: "https://github.com/eyaltoledano/claude-task-master"
license: "Other"
stars: 28230
last_push: "2026-04-28"
archived: false
tags: ["license-unclear"]
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Task Master

**What:** Task-management system for coding agents.

**Why:** Reusable instructions that make agents behave.

**Category:** Scaffolds & templates · **Stack layer:** harness

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
npm install -g task-master-ai
```

2. [any] source: README (auto-extracted); status: unverified, not executed

```bash
npm install task-master-ai
```

3. [any] source: README (auto-extracted); status: unverified, not executed

```bash
npx task-master init
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
npm uninstall -g task-master-ai
```

## Links

- Homepage: https://tryhamster.com
- Repo: https://github.com/eyaltoledano/claude-task-master
- README: https://github.com/eyaltoledano/claude-task-master#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "openclaw"
name: "OpenClaw"
kind: "repo"
tier: "catalog"
category: "general"
category_label: "General & personal agents"
stack_layer: "harness"
homepage: "https://openclaw.ai"
repo: "https://github.com/openclaw/openclaw"
license: "MIT"
stars: 392108
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# OpenClaw

**What:** Personal agent that runs on your machine and chats anywhere.

**Why:** Lets a model take actions for you, not just chat.

**Category:** General & personal agents · **Stack layer:** harness

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://openclaw.ai
- Repo: https://github.com/openclaw/openclaw
- README: https://github.com/openclaw/openclaw#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "autogpt"
name: "AutoGPT"
kind: "repo"
tier: "catalog"
category: "general"
category_label: "General & personal agents"
stack_layer: "harness"
homepage: "https://agpt.co"
repo: "https://github.com/Significant-Gravitas/AutoGPT"
license: "Other"
stars: 187599
last_push: "2026-10-15"
archived: false
tags: ["license-unclear"]
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# AutoGPT

**What:** Platform for building autonomous agents.

**Why:** Lets a model take actions for you, not just chat.

**Category:** General & personal agents · **Stack layer:** harness

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://agpt.co
- Repo: https://github.com/Significant-Gravitas/AutoGPT
- README: https://github.com/Significant-Gravitas/AutoGPT#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "browser-use"
name: "Browser Use"
kind: "repo"
tier: "catalog"
category: "general"
category_label: "General & personal agents"
stack_layer: "harness"
homepage: "https://browser-use.com"
repo: "https://github.com/browser-use/browser-use"
license: "MIT"
stars: 118088
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Browser Use

**What:** Let an AI agent drive a web browser.

**Why:** Lets a model take actions for you, not just chat.

**Category:** General & personal agents · **Stack layer:** harness

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://browser-use.com
- Repo: https://github.com/browser-use/browser-use
- README: https://github.com/browser-use/browser-use#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "deerflow"
name: "DeerFlow"
kind: "repo"
tier: "catalog"
category: "general"
category_label: "General & personal agents"
stack_layer: "harness"
homepage: "https://deerflow.tech"
repo: "https://github.com/bytedance/deer-flow"
license: "MIT"
stars: 83911
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# DeerFlow

**What:** Long-running research and coding super-agent.

**Why:** Lets a model take actions for you, not just chat.

**Category:** General & personal agents · **Stack layer:** harness

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://deerflow.tech
- Repo: https://github.com/bytedance/deer-flow
- README: https://github.com/bytedance/deer-flow#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "open-interpreter"
name: "Open Interpreter"
kind: "repo"
tier: "catalog"
category: "general"
category_label: "General & personal agents"
stack_layer: "harness"
homepage: "http://openinterpreter.com/"
repo: "https://github.com/openinterpreter/openinterpreter"
license: "Apache-2.0"
stars: 68582
last_push: "2026-10-11"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Open Interpreter

**What:** Agent that runs code on your computer, for open models.

**Why:** Lets a model take actions for you, not just chat.

**Category:** General & personal agents · **Stack layer:** harness

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
curl -fsSL https://www.openinterpreter.com/install | sh
```

2. [windows] source: README (auto-extracted); status: unverified, not executed

```bash
irm https://www.openinterpreter.com/install.ps1 | iex
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: http://openinterpreter.com/
- Repo: https://github.com/openinterpreter/openinterpreter
- README: https://github.com/openinterpreter/openinterpreter#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "openmanus"
name: "OpenManus"
kind: "repo"
tier: "catalog"
category: "general"
category_label: "General & personal agents"
stack_layer: "harness"
homepage: "https://openmanus.github.io/"
repo: "https://github.com/FoundationAgents/OpenManus"
license: "MIT"
stars: 58673
last_push: "2026-09-30"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# OpenManus

**What:** Open-source general agent (Manus-style).

**Why:** Lets a model take actions for you, not just chat.

**Category:** General & personal agents · **Stack layer:** harness

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://openmanus.github.io/
- Repo: https://github.com/FoundationAgents/OpenManus
- README: https://github.com/FoundationAgents/OpenManus#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "nanobot"
name: "nanobot"
kind: "repo"
tier: "catalog"
category: "general"
category_label: "General & personal agents"
stack_layer: "harness"
homepage: "https://nanobot.wiki"
repo: "https://github.com/HKUDS/nanobot"
license: "MIT"
stars: 49063
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# nanobot

**What:** Ultra-light self-hosted personal agent.

**Why:** Lets a model take actions for you, not just chat.

**Category:** General & personal agents · **Stack layer:** harness

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
curl -fsSL https://raw.githubusercontent.com/HKUDS/nanobot/main/scripts/install.sh | sh
```

2. [windows] source: README (auto-extracted); status: unverified, not executed

```bash
irm https://raw.githubusercontent.com/HKUDS/nanobot/main/scripts/install.ps1 | iex
```

3. [any] source: README (auto-extracted); status: unverified, not executed

```bash
curl -fsSL https://raw.githubusercontent.com/HKUDS/nanobot/main/scripts/install.sh | sh -s -- --dry-run
```

4. [any] source: README (auto-extracted); status: unverified, not executed

```bash
uv tool install nanobot-ai
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
uv tool uninstall nanobot-ai
```

## Links

- Homepage: https://nanobot.wiki
- Repo: https://github.com/HKUDS/nanobot
- README: https://github.com/HKUDS/nanobot#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "ui-tars-desktop"
name: "UI-TARS Desktop"
kind: "repo"
tier: "catalog"
category: "general"
category_label: "General & personal agents"
stack_layer: "harness"
homepage: "https://agent-tars.com"
repo: "https://github.com/bytedance/UI-TARS-desktop"
license: "Apache-2.0"
stars: 39287
last_push: "2026-10-09"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# UI-TARS Desktop

**What:** Multimodal agent that operates your desktop.

**Why:** Lets a model take actions for you, not just chat.

**Category:** General & personal agents · **Stack layer:** harness

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
npm install @agent-tars/cli@latest -g
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://agent-tars.com
- Repo: https://github.com/bytedance/UI-TARS-desktop
- README: https://github.com/bytedance/UI-TARS-desktop#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "khoj"
name: "Khoj"
kind: "repo"
tier: "catalog"
category: "general"
category_label: "General & personal agents"
stack_layer: "harness"
homepage: "https://khoj.dev"
repo: "https://github.com/khoj-ai/khoj"
license: "AGPL-3.0"
stars: 37690
last_push: "2026-08-02"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Khoj

**What:** Self-hostable AI second brain over your docs and the web.

**Why:** Lets a model take actions for you, not just chat.

**Category:** General & personal agents · **Stack layer:** harness

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://khoj.dev
- Repo: https://github.com/khoj-ai/khoj
- README: https://github.com/khoj-ai/khoj#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "perplexica"
name: "Perplexica"
kind: "repo"
tier: "catalog"
category: "general"
category_label: "General & personal agents"
stack_layer: "harness"
homepage: null
repo: "https://github.com/ItzCrazyKns/Vane"
license: "MIT"
stars: 37346
last_push: "2026-09-01"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Perplexica

**What:** Open answering engine (formerly Perplexica).

**Why:** Lets a model take actions for you, not just chat.

**Category:** General & personal agents · **Stack layer:** harness

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
docker run -d -p 3000:3000 -v vane-data:/home/vane/data --name vane itzcrazykns1337/vane:latest
```

2. [any] source: README (auto-extracted); status: unverified, not executed

```bash
git clone https://github.com/ItzCrazyKns/Vane.git
```

3. [any] source: README (auto-extracted); status: unverified, not executed

```bash
docker run -d -p 3000:3000 -v vane-data:/home/vane/data --name vane vane
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
docker rm -f vane
```

2. source: derived inverse of install command

```bash
rm -rf Vane
```

## Links

- Repo: https://github.com/ItzCrazyKns/Vane
- README: https://github.com/ItzCrazyKns/Vane#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "nanoclaw"
name: "NanoClaw"
kind: "repo"
tier: "catalog"
category: "general"
category_label: "General & personal agents"
stack_layer: "harness"
homepage: "https://nanoclaw.dev"
repo: "https://github.com/nanocoai/nanoclaw"
license: "MIT"
stars: 30954
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# NanoClaw

**What:** Lightweight, container-sandboxed OpenClaw alternative.

**Why:** Lets a model take actions for you, not just chat.

**Category:** General & personal agents · **Stack layer:** harness

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
git clone https://github.com/nanocoai/nanoclaw.git nanoclaw-v2
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
rm -rf nanoclaw-v2
```

## Links

- Homepage: https://nanoclaw.dev
- Repo: https://github.com/nanocoai/nanoclaw
- README: https://github.com/nanocoai/nanoclaw#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "gpt-researcher"
name: "GPT Researcher"
kind: "repo"
tier: "catalog"
category: "general"
category_label: "General & personal agents"
stack_layer: "harness"
homepage: "https://gptr.dev"
repo: "https://github.com/assafelovic/gpt-researcher"
license: "Apache-2.0"
stars: 30114
last_push: "2026-10-10"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# GPT Researcher

**What:** Agent that writes deep research reports.

**Why:** Lets a model take actions for you, not just chat.

**Category:** General & personal agents · **Stack layer:** harness

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
npx skills add assafelovic/gpt-researcher
```

2. [any] source: README (auto-extracted); status: unverified, not executed

```bash
git clone https://github.com/assafelovic/gpt-researcher.git
```

3. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install gpt-researcher
```

4. [any] source: README (auto-extracted); status: unverified, not executed

```bash
docker compose up --build
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
rm -rf gpt-researcher
```

2. source: derived inverse of install command

```bash
pip uninstall -y gpt-researcher
```

## Links

- Homepage: https://gptr.dev
- Repo: https://github.com/assafelovic/gpt-researcher
- README: https://github.com/assafelovic/gpt-researcher#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "cua"
name: "Cua"
kind: "repo"
tier: "catalog"
category: "general"
category_label: "General & personal agents"
stack_layer: "harness"
homepage: "https://cua.ai"
repo: "https://github.com/trycua/cua"
license: "MIT"
stars: 29857
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Cua

**What:** Open-source computer-use drivers and sandboxes.

**Why:** Lets a model take actions for you, not just chat.

**Category:** General & personal agents · **Stack layer:** harness

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://cua.ai
- Repo: https://github.com/trycua/cua
- README: https://github.com/trycua/cua#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "autogen"
name: "AutoGen"
kind: "repo"
tier: "catalog"
category: "frameworks"
category_label: "Agent frameworks"
stack_layer: "harness"
homepage: "https://microsoft.github.io/autogen/"
repo: "https://github.com/microsoft/autogen"
license: "CC-BY-4.0"
stars: 61426
last_push: "2026-04-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# AutoGen

**What:** Microsoft's multi-agent programming framework.

**Why:** Building blocks for your own agents.

**Category:** Agent frameworks · **Stack layer:** harness

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install -U "autogen-agentchat" "autogen-ext[openai]"
```

2. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install -U "autogenstudio"
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
pip uninstall -y autogen-agentchat
```

2. source: derived inverse of install command

```bash
pip uninstall -y autogenstudio
```

## Links

- Homepage: https://microsoft.github.io/autogen/
- Repo: https://github.com/microsoft/autogen
- README: https://github.com/microsoft/autogen#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "crewai"
name: "CrewAI"
kind: "repo"
tier: "catalog"
category: "frameworks"
category_label: "Agent frameworks"
stack_layer: "harness"
homepage: "https://crewai.com"
repo: "https://github.com/crewAIInc/crewAI"
license: "MIT"
stars: 59740
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# CrewAI

**What:** Role-based multi-agent framework.

**Why:** Building blocks for your own agents.

**Category:** Agent frameworks · **Stack layer:** harness

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
curl -LsSf https://astral.sh/uv/install.sh | sh
```

2. [any] source: README (auto-extracted); status: unverified, not executed

```bash
uv tool install crewai
```

3. [any] source: README (auto-extracted); status: unverified, not executed

```bash
uv tool install crewai --upgrade
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
uv tool uninstall crewai
```

## Links

- Homepage: https://crewai.com
- Repo: https://github.com/crewAIInc/crewAI
- README: https://github.com/crewAIInc/crewAI#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "langgraph"
name: "LangGraph"
kind: "repo"
tier: "catalog"
category: "frameworks"
category_label: "Agent frameworks"
stack_layer: "harness"
homepage: "https://docs.langchain.com/oss/python/langgraph/"
repo: "https://github.com/langchain-ai/langgraph"
license: "MIT"
stars: 43319
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# LangGraph

**What:** Build stateful, resilient agent graphs.

**Why:** Building blocks for your own agents.

**Category:** Agent frameworks · **Stack layer:** harness

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://docs.langchain.com/oss/python/langgraph/
- Repo: https://github.com/langchain-ai/langgraph
- README: https://github.com/langchain-ai/langgraph#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "agno"
name: "Agno"
kind: "repo"
tier: "catalog"
category: "frameworks"
category_label: "Agent frameworks"
stack_layer: "harness"
homepage: "https://docs.agno.com"
repo: "https://github.com/agno-agi/agno"
license: "Apache-2.0"
stars: 42754
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Agno

**What:** Build and run agent systems in Python.

**Why:** Building blocks for your own agents.

**Category:** Agent frameworks · **Stack layer:** harness

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://docs.agno.com
- Repo: https://github.com/agno-agi/agno
- README: https://github.com/agno-agi/agno#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "dspy"
name: "DSPy"
kind: "repo"
tier: "catalog"
category: "frameworks"
category_label: "Agent frameworks"
stack_layer: "harness"
homepage: "https://dspy.ai"
repo: "https://github.com/stanfordnlp/dspy"
license: "MIT"
stars: 38652
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# DSPy

**What:** Program LLMs instead of hand-writing prompts.

**Why:** Building blocks for your own agents.

**Category:** Agent frameworks · **Stack layer:** harness

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install dspy
```

2. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install git+https://github.com/stanfordnlp/dspy.git
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
pip uninstall -y dspy
```

## Links

- Homepage: https://dspy.ai
- Repo: https://github.com/stanfordnlp/dspy
- README: https://github.com/stanfordnlp/dspy#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "openai-agents-sdk"
name: "OpenAI Agents SDK"
kind: "repo"
tier: "catalog"
category: "frameworks"
category_label: "Agent frameworks"
stack_layer: "harness"
homepage: "https://openai.github.io/openai-agents-python/"
repo: "https://github.com/openai/openai-agents-python"
license: "MIT"
stars: 30057
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# OpenAI Agents SDK

**What:** OpenAI's lightweight multi-agent SDK.

**Why:** Building blocks for your own agents.

**Category:** Agent frameworks · **Stack layer:** harness

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://openai.github.io/openai-agents-python/
- Repo: https://github.com/openai/openai-agents-python
- README: https://github.com/openai/openai-agents-python#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "smolagents"
name: "smolagents"
kind: "repo"
tier: "catalog"
category: "frameworks"
category_label: "Agent frameworks"
stack_layer: "harness"
homepage: "https://huggingface.co/docs/smolagents"
repo: "https://github.com/huggingface/smolagents"
license: "Apache-2.0"
stars: 29865
last_push: "2026-10-06"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# smolagents

**What:** Tiny library for agents that think in code.

**Why:** Building blocks for your own agents.

**Category:** Agent frameworks · **Stack layer:** harness

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install "smolagents[toolkit]"
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
pip uninstall -y smolagents
```

## Links

- Homepage: https://huggingface.co/docs/smolagents
- Repo: https://github.com/huggingface/smolagents
- README: https://github.com/huggingface/smolagents#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "mastra"
name: "Mastra"
kind: "repo"
tier: "catalog"
category: "frameworks"
category_label: "Agent frameworks"
stack_layer: "harness"
homepage: "https://mastra.ai"
repo: "https://github.com/mastra-ai/mastra"
license: "Other"
stars: 28834
last_push: "2026-10-15"
archived: false
tags: ["license-unclear"]
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Mastra

**What:** TypeScript framework for agents and workflows.

**Why:** Building blocks for your own agents.

**Category:** Agent frameworks · **Stack layer:** harness

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://mastra.ai
- Repo: https://github.com/mastra-ai/mastra
- README: https://github.com/mastra-ai/mastra#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "vercel-ai-sdk"
name: "Vercel AI SDK"
kind: "repo"
tier: "catalog"
category: "frameworks"
category_label: "Agent frameworks"
stack_layer: "harness"
homepage: "https://ai-sdk.dev"
repo: "https://github.com/vercel/ai"
license: "Other"
stars: 27335
last_push: "2026-10-15"
archived: false
tags: ["license-unclear"]
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Vercel AI SDK

**What:** TypeScript toolkit for AI apps and agents.

**Why:** Building blocks for your own agents.

**Category:** Agent frameworks · **Stack layer:** harness

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
npm install ai
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://ai-sdk.dev
- Repo: https://github.com/vercel/ai
- README: https://github.com/vercel/ai#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "haystack"
name: "Haystack"
kind: "repo"
tier: "catalog"
category: "frameworks"
category_label: "Agent frameworks"
stack_layer: "harness"
homepage: "https://haystack.deepset.ai"
repo: "https://github.com/deepset-ai/haystack"
license: "Apache-2.0"
stars: 26744
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Haystack

**What:** Orchestration framework for RAG and agents.

**Why:** Building blocks for your own agents.

**Category:** Agent frameworks · **Stack layer:** harness

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install haystack-ai
```

2. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install --pre haystack-ai
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
pip uninstall -y haystack-ai
```

## Links

- Homepage: https://haystack.deepset.ai
- Repo: https://github.com/deepset-ai/haystack
- README: https://github.com/deepset-ai/haystack#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "letta"
name: "Letta"
kind: "repo"
tier: "catalog"
category: "frameworks"
category_label: "Agent frameworks"
stack_layer: "harness"
homepage: "https://docs.letta.com/"
repo: "https://github.com/letta-ai/letta"
license: "Apache-2.0"
stars: 25156
last_push: "2026-09-10"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Letta

**What:** Stateful agents with long-term memory (ex-MemGPT).

**Why:** Building blocks for your own agents.

**Category:** Agent frameworks · **Stack layer:** harness

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
npm install -g @letta-ai/letta-code
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
npm uninstall -g @letta-ai/letta-code
```

## Links

- Homepage: https://docs.letta.com/
- Repo: https://github.com/letta-ai/letta
- README: https://github.com/letta-ai/letta#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "google-adk"
name: "Google ADK"
kind: "repo"
tier: "catalog"
category: "frameworks"
category_label: "Agent frameworks"
stack_layer: "harness"
homepage: "https://google.github.io/adk-docs/"
repo: "https://github.com/google/adk-python"
license: "Apache-2.0"
stars: 21862
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Google ADK

**What:** Google's code-first agent development kit.

**Why:** Building blocks for your own agents.

**Category:** Agent frameworks · **Stack layer:** harness

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://google.github.io/adk-docs/
- Repo: https://github.com/google/adk-python
- README: https://github.com/google/adk-python#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "pydantic-ai"
name: "Pydantic AI"
kind: "repo"
tier: "catalog"
category: "frameworks"
category_label: "Agent frameworks"
stack_layer: "harness"
homepage: "https://pydantic.dev/pydantic-ai"
repo: "https://github.com/pydantic/pydantic-ai"
license: "MIT"
stars: 20643
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Pydantic AI

**What:** Typed Python agent framework.

**Why:** Building blocks for your own agents.

**Category:** Agent frameworks · **Stack layer:** harness

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://pydantic.dev/pydantic-ai
- Repo: https://github.com/pydantic/pydantic-ai
- README: https://github.com/pydantic/pydantic-ai#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "claude-mem"
name: "claude-mem"
kind: "repo"
tier: "catalog"
category: "memory"
category_label: "Memory"
stack_layer: "memory"
homepage: "https://claude-mem.ai"
repo: "https://github.com/thedotmack/claude-mem"
license: "Apache-2.0"
stars: 100993
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# claude-mem

**What:** Captures agent sessions and replays context later.

**Why:** Lets your agent remember across sessions.

**Category:** Memory · **Stack layer:** memory

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
npx claude-mem install --ide grok-bot
```

2. [any] source: README (auto-extracted); status: unverified, not executed

```bash
npx claude-mem install
```

3. [any] source: README (auto-extracted); status: unverified, not executed

```bash
npx claude-mem install --ide opencode
```

4. [any] source: README (auto-extracted); status: unverified, not executed

```bash
npx claude-mem install --ide t3code
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://claude-mem.ai
- Repo: https://github.com/thedotmack/claude-mem
- README: https://github.com/thedotmack/claude-mem#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "cognee"
name: "Cognee"
kind: "repo"
tier: "catalog"
category: "memory"
category_label: "Memory"
stack_layer: "memory"
homepage: "https://www.cognee.ai"
repo: "https://github.com/topoteretes/cognee"
license: "Apache-2.0"
stars: 32356
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Cognee

**What:** Knowledge-graph memory for agents.

**Why:** Lets your agent remember across sessions.

**Category:** Memory · **Stack layer:** memory

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
uv pip install "cognee[gliner]"
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
uv pip uninstall cognee
```

## Links

- Homepage: https://www.cognee.ai
- Repo: https://github.com/topoteretes/cognee
- README: https://github.com/topoteretes/cognee#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "graphiti"
name: "Graphiti"
kind: "repo"
tier: "catalog"
category: "memory"
category_label: "Memory"
stack_layer: "memory"
homepage: "https://help.getzep.com/graphiti"
repo: "https://github.com/getzep/graphiti"
license: "Apache-2.0"
stars: 31795
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Graphiti

**What:** Real-time temporal knowledge graphs for agents.

**Why:** Lets your agent remember across sessions.

**Category:** Memory · **Stack layer:** memory

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install graphiti-core
```

2. [any] source: README (auto-extracted); status: unverified, not executed

```bash
uv add graphiti-core
```

3. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install graphiti-core[falkordb]
```

4. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install graphiti-core[kuzu]
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
pip uninstall -y graphiti-core
```

## Links

- Homepage: https://help.getzep.com/graphiti
- Repo: https://github.com/getzep/graphiti
- README: https://github.com/getzep/graphiti#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "supermemory"
name: "Supermemory"
kind: "repo"
tier: "catalog"
category: "memory"
category_label: "Memory"
stack_layer: "memory"
homepage: "https://supermemory.ai/docs"
repo: "https://github.com/supermemoryai/supermemory"
license: "MIT"
stars: 31236
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Supermemory

**What:** Fast memory engine and app, can run locally.

**Why:** Lets your agent remember across sessions.

**Category:** Memory · **Stack layer:** memory

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
npm install supermemory
```

2. [any] source: README (auto-extracted); status: unverified, not executed

```bash
curl -fsSL https://supermemory.ai/install | bash
```

3. [any] source: README (auto-extracted); status: unverified, not executed

```bash
docker compose up -d --wait --wait-timeout 180
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://supermemory.ai/docs
- Repo: https://github.com/supermemoryai/supermemory
- README: https://github.com/supermemoryai/supermemory#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "memos"
name: "MemOS"
kind: "repo"
tier: "catalog"
category: "memory"
category_label: "Memory"
stack_layer: "memory"
homepage: "https://memos.openmem.net"
repo: "https://github.com/MemTensor/MemOS"
license: "Apache-2.0"
stars: 11878
last_push: "2026-10-10"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# MemOS

**What:** Memory operating system for LLM agents.

**Why:** Lets your agent remember across sessions.

**Category:** Memory · **Stack layer:** memory

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://memos.openmem.net
- Repo: https://github.com/MemTensor/MemOS
- README: https://github.com/MemTensor/MemOS#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "honcho"
name: "Honcho"
kind: "repo"
tier: "catalog"
category: "memory"
category_label: "Memory"
stack_layer: "memory"
homepage: "https://honcho.dev/docs"
repo: "https://github.com/plastic-labs/honcho"
license: "AGPL-3.0"
stars: 7633
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Honcho

**What:** Memory library that models users across sessions.

**Why:** Lets your agent remember across sessions.

**Category:** Memory · **Stack layer:** memory

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
git clone https://github.com/plastic-labs/honcho.git
```

2. [any] source: README (auto-extracted); status: unverified, not executed

```bash
docker compose up
```

3. [any] source: README (auto-extracted); status: unverified, not executed

```bash
docker compose up -d database
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
rm -rf honcho
```

## Links

- Homepage: https://honcho.dev/docs
- Repo: https://github.com/plastic-labs/honcho
- README: https://github.com/plastic-labs/honcho#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "basic-memory"
name: "Basic Memory"
kind: "repo"
tier: "catalog"
category: "memory"
category_label: "Memory"
stack_layer: "memory"
homepage: "https://basicmemory.com"
repo: "https://github.com/basicmachines-co/basic-memory"
license: "AGPL-3.0"
stars: 4231
last_push: "2026-10-14"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Basic Memory

**What:** Markdown-file memory your agent reads and writes.

**Why:** Lets your agent remember across sessions.

**Category:** Memory · **Stack layer:** memory

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
uv tool install basic-memory --prerelease=allow
```

2. [any] source: README (auto-extracted); status: unverified, not executed

```bash
uv tool install "basic-memory[milvus]" --prerelease=allow
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
uv tool uninstall basic-memory
```

## Links

- Homepage: https://basicmemory.com
- Repo: https://github.com/basicmachines-co/basic-memory
- README: https://github.com/basicmachines-co/basic-memory#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "memobase"
name: "Memobase"
kind: "repo"
tier: "catalog"
category: "memory"
category_label: "Memory"
stack_layer: "memory"
homepage: "https://memobase.io"
repo: "https://github.com/memodb-io/memobase"
license: "Apache-2.0"
stars: 2931
last_push: "2026-01-11"
archived: false
tags: ["slow-activity"]
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Memobase

**What:** User-profile memory for chat apps.

**Why:** Lets your agent remember across sessions.

**Category:** Memory · **Stack layer:** memory

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://memobase.io
- Repo: https://github.com/memodb-io/memobase
- README: https://github.com/memodb-io/memobase#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "memsearch"
name: "memsearch"
kind: "repo"
tier: "catalog"
category: "memory"
category_label: "Memory"
stack_layer: "memory"
homepage: "https://zilliztech.github.io/memsearch/"
repo: "https://github.com/zilliztech/memsearch"
license: "MIT"
stars: 2751
last_push: "2026-10-09"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# memsearch

**What:** Semantic search over agent memory files.

**Why:** Lets your agent remember across sessions.

**Category:** Memory · **Stack layer:** memory

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
git clone --depth 1 https://github.com/zilliztech/memsearch.git
```

2. [any] source: README (auto-extracted); status: unverified, not executed

```bash
uv tool install "memsearch[onnx]"
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
rm -rf https://github.com/zilliztech/memsearch.git
```

2. source: derived inverse of install command

```bash
uv tool uninstall memsearch
```

## Links

- Homepage: https://zilliztech.github.io/memsearch/
- Repo: https://github.com/zilliztech/memsearch
- README: https://github.com/zilliztech/memsearch#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "mcp-memory-service"
name: "MCP Memory Service"
kind: "repo"
tier: "catalog"
category: "memory"
category_label: "Memory"
stack_layer: "memory"
homepage: null
repo: "https://github.com/doobidoo/mcp-memory-service"
license: "Apache-2.0"
stars: 2018
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# MCP Memory Service

**What:** Persistent memory exposed as an MCP server.

**Why:** Lets your agent remember across sessions.

**Category:** Memory · **Stack layer:** memory

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install mcp-memory-service
```

2. [any] source: README (auto-extracted); status: unverified, not executed

```bash
git clone https://github.com/doobidoo/mcp-memory-service.git
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
pip uninstall -y mcp-memory-service
```

2. source: derived inverse of install command

```bash
rm -rf mcp-memory-service
```

## Links

- Repo: https://github.com/doobidoo/mcp-memory-service
- README: https://github.com/doobidoo/mcp-memory-service#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "marker"
name: "Marker"
kind: "repo"
tier: "catalog"
category: "rag"
category_label: "RAG & document parsing"
stack_layer: "memory"
homepage: "https://www.datalab.to"
repo: "https://github.com/datalab-to/marker"
license: "Apache-2.0"
stars: 40473
last_push: "2026-10-14"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Marker

**What:** Fast, accurate PDF-to-markdown converter.

**Why:** Feeds your own documents to the model.

**Category:** RAG & document parsing · **Stack layer:** memory

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install marker-pdf
```

2. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install marker-pdf[full]
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
pip uninstall -y marker-pdf
```

## Links

- Homepage: https://www.datalab.to
- Repo: https://github.com/datalab-to/marker
- README: https://github.com/datalab-to/marker#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "lightrag"
name: "LightRAG"
kind: "repo"
tier: "catalog"
category: "rag"
category_label: "RAG & document parsing"
stack_layer: "memory"
homepage: "https://arxiv.org/abs/2410.05779"
repo: "https://github.com/HKUDS/LightRAG"
license: "MIT"
stars: 40153
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# LightRAG

**What:** Simple, fast graph-based RAG.

**Why:** Feeds your own documents to the model.

**Category:** RAG & document parsing · **Stack layer:** memory

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
uv tool install "lightrag-hku[api]"
```

2. [any] source: README (auto-extracted); status: unverified, not executed

```bash
uv pip install lightrag-hku
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
uv tool uninstall lightrag-hku
```

2. source: derived inverse of install command

```bash
uv pip uninstall lightrag-hku
```

## Links

- Homepage: https://arxiv.org/abs/2410.05779
- Repo: https://github.com/HKUDS/LightRAG
- README: https://github.com/HKUDS/LightRAG#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "qdrant"
name: "Qdrant"
kind: "repo"
tier: "catalog"
category: "rag"
category_label: "RAG & document parsing"
stack_layer: "memory"
homepage: "https://qdrant.tech"
repo: "https://github.com/qdrant/qdrant"
license: "Apache-2.0"
stars: 35085
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Qdrant

**What:** High-performance vector database.

**Why:** Feeds your own documents to the model.

**Category:** RAG & document parsing · **Stack layer:** memory

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://qdrant.tech
- Repo: https://github.com/qdrant/qdrant
- README: https://github.com/qdrant/qdrant#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "chroma"
name: "Chroma"
kind: "repo"
tier: "catalog"
category: "rag"
category_label: "RAG & document parsing"
stack_layer: "memory"
homepage: "https://www.trychroma.com/"
repo: "https://github.com/chroma-core/chroma"
license: "Apache-2.0"
stars: 29510
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Chroma

**What:** Open-source embedding database.

**Why:** Feeds your own documents to the model.

**Category:** RAG & document parsing · **Stack layer:** memory

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://www.trychroma.com/
- Repo: https://github.com/chroma-core/chroma
- README: https://github.com/chroma-core/chroma#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "pgvector"
name: "pgvector"
kind: "repo"
tier: "catalog"
category: "rag"
category_label: "RAG & document parsing"
stack_layer: "memory"
homepage: null
repo: "https://github.com/pgvector/pgvector"
license: "Other"
stars: 23371
last_push: "2026-10-15"
archived: false
tags: ["license-unclear"]
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# pgvector

**What:** Vector search inside Postgres.

**Why:** Feeds your own documents to the model.

**Category:** RAG & document parsing · **Stack layer:** memory

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Repo: https://github.com/pgvector/pgvector
- README: https://github.com/pgvector/pgvector#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "lancedb"
name: "LanceDB"
kind: "repo"
tier: "catalog"
category: "rag"
category_label: "RAG & document parsing"
stack_layer: "memory"
homepage: "https://lancedb.com/docs"
repo: "https://github.com/lancedb/lancedb"
license: "Apache-2.0"
stars: 11680
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# LanceDB

**What:** Embedded multimodal vector database.

**Why:** Feeds your own documents to the model.

**Category:** RAG & document parsing · **Stack layer:** memory

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://lancedb.com/docs
- Repo: https://github.com/lancedb/lancedb
- README: https://github.com/lancedb/lancedb#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "sqlite-vec"
name: "sqlite-vec"
kind: "repo"
tier: "catalog"
category: "rag"
category_label: "RAG & document parsing"
stack_layer: "memory"
homepage: null
repo: "https://github.com/asg017/sqlite-vec"
license: "Apache-2.0"
stars: 8189
last_push: "2026-05-18"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# sqlite-vec

**What:** Vector search as a tiny SQLite extension.

**Why:** Feeds your own documents to the model.

**Category:** RAG & document parsing · **Stack layer:** memory

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Repo: https://github.com/asg017/sqlite-vec
- README: https://github.com/asg017/sqlite-vec#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "markitdown"
name: "MarkItDown"
kind: "repo"
tier: "catalog"
category: "rag"
category_label: "RAG & document parsing"
stack_layer: "memory"
homepage: null
repo: "https://github.com/microsoft/markitdown"
license: "MIT"
stars: 190405
last_push: "2026-10-04"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# MarkItDown

**What:** Convert files and Office docs to markdown.

**Why:** Feeds your own documents to the model.

**Category:** RAG & document parsing · **Stack layer:** memory

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
git clone git@github.com:microsoft/markitdown.git
```

2. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install hatch
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
rm -rf markitdown
```

2. source: derived inverse of install command

```bash
pip uninstall -y hatch
```

## Links

- Repo: https://github.com/microsoft/markitdown
- README: https://github.com/microsoft/markitdown#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "ragflow"
name: "RAGFlow"
kind: "repo"
tier: "catalog"
category: "rag"
category_label: "RAG & document parsing"
stack_layer: "memory"
homepage: "https://ragflow.io"
repo: "https://github.com/infiniflow/ragflow"
license: "Apache-2.0"
stars: 92283
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# RAGFlow

**What:** Deep-document RAG engine with a UI.

**Why:** Feeds your own documents to the model.

**Category:** RAG & document parsing · **Stack layer:** memory

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
git clone https://github.com/infiniflow/ragflow.git
```

2. [any] source: README (auto-extracted); status: unverified, not executed

```bash
docker compose -f docker-compose.yml up -d
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
rm -rf ragflow
```

## Links

- Homepage: https://ragflow.io
- Repo: https://github.com/infiniflow/ragflow
- README: https://github.com/infiniflow/ragflow#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "paddleocr"
name: "PaddleOCR"
kind: "repo"
tier: "catalog"
category: "rag"
category_label: "RAG & document parsing"
stack_layer: "memory"
homepage: "https://www.paddleocr.com"
repo: "https://github.com/PaddlePaddle/PaddleOCR"
license: "Apache-2.0"
stars: 91178
last_push: "2026-09-16"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# PaddleOCR

**What:** OCR and document parsing toolkit.

**Why:** Feeds your own documents to the model.

**Category:** RAG & document parsing · **Stack layer:** memory

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://www.paddleocr.com
- Repo: https://github.com/PaddlePaddle/PaddleOCR
- README: https://github.com/PaddlePaddle/PaddleOCR#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "mineru"
name: "MinerU"
kind: "repo"
tier: "catalog"
category: "rag"
category_label: "RAG & document parsing"
stack_layer: "memory"
homepage: "https://opendatalab.github.io/MinerU/"
repo: "https://github.com/opendatalab/MinerU"
license: "Other"
stars: 81815
last_push: "2026-10-14"
archived: false
tags: ["license-unclear"]
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# MinerU

**What:** Converts complex PDFs to markdown or JSON.

**Why:** Feeds your own documents to the model.

**Category:** RAG & document parsing · **Stack layer:** memory

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
uv tool install --python 3.12 "mineru>=4.0,<5"
```

2. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pipx install "mineru>=4.0,<5"
```

3. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pipx install --python python3.12 "mineru>=4.0,<5"
```

4. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pipx install --python 3.12 --fetch-python=missing "mineru>=4.0,<5"
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
uv tool uninstall mineru
```

2. source: derived inverse of install command

```bash
pipx uninstall mineru
```

## Links

- Homepage: https://opendatalab.github.io/MinerU/
- Repo: https://github.com/opendatalab/MinerU
- README: https://github.com/opendatalab/MinerU#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "anythingllm"
name: "AnythingLLM"
kind: "repo"
tier: "catalog"
category: "rag"
category_label: "RAG & document parsing"
stack_layer: "memory"
homepage: "https://anythingllm.com"
repo: "https://github.com/Mintplex-Labs/anything-llm"
license: "MIT"
stars: 67160
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# AnythingLLM

**What:** All-in-one desktop app for chat with your docs.

**Why:** Feeds your own documents to the model.

**Category:** RAG & document parsing · **Stack layer:** memory

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://anythingllm.com
- Repo: https://github.com/Mintplex-Labs/anything-llm
- README: https://github.com/Mintplex-Labs/anything-llm#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "meilisearch"
name: "Meilisearch"
kind: "repo"
tier: "catalog"
category: "rag"
category_label: "RAG & document parsing"
stack_layer: "memory"
homepage: "https://www.meilisearch.com"
repo: "https://github.com/meilisearch/meilisearch"
license: "Other"
stars: 59577
last_push: "2026-10-15"
archived: false
tags: ["license-unclear"]
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Meilisearch

**What:** Fast search engine with hybrid vector search.

**Why:** Feeds your own documents to the model.

**Category:** RAG & document parsing · **Stack layer:** memory

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://www.meilisearch.com
- Repo: https://github.com/meilisearch/meilisearch
- README: https://github.com/meilisearch/meilisearch#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "strands-decider"
name: "Strands Decider"
kind: "repo"
tier: "catalog"
category: "routing"
category_label: "Routing & gateways"
stack_layer: "runtime"
homepage: "https://strandsagents.com/docs/labs/"
repo: "https://github.com/strands-labs/strands-decider"
license: "Apache-2.0"
stars: 655
last_push: "2026-10-16"
archived: false
tags: []
seen_in_videos: ["q9QJlZBgOGE"]
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-16"
---

# Strands Decider

**What:** Small decision model that routes agent choices.

**Why:** Sends each request to the right model.

**Category:** Routing & gateways · **Stack layer:** runtime

## Status

Catalog entry. Existence and repo metadata checked 2026-10-16 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install strands-decider
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
pip uninstall -y strands-decider
```

## Links

- Homepage: https://strandsagents.com/docs/labs/
- Repo: https://github.com/strands-labs/strands-decider
- README: https://github.com/strands-labs/strands-decider#readme
- Video: https://www.youtube.com/watch?v=q9QJlZBgOGE


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "new-api"
name: "New API"
kind: "repo"
tier: "catalog"
category: "routing"
category_label: "Routing & gateways"
stack_layer: "runtime"
homepage: "https://www.newapi.ai"
repo: "https://github.com/QuantumNous/new-api"
license: "AGPL-3.0"
stars: 50036
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# New API

**What:** Unified gateway that converts many LLM APIs.

**Why:** Sends each request to the right model.

**Category:** Routing & gateways · **Stack layer:** runtime

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://www.newapi.ai
- Repo: https://github.com/QuantumNous/new-api
- README: https://github.com/QuantumNous/new-api#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "one-api"
name: "One API"
kind: "repo"
tier: "catalog"
category: "routing"
category_label: "Routing & gateways"
stack_layer: "runtime"
homepage: "https://oneapi.justsong.cn/"
repo: "https://github.com/songquanpeng/one-api"
license: "MIT"
stars: 37168
last_push: "2026-01-09"
archived: false
tags: ["slow-activity"]
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# One API

**What:** LLM API management and distribution gateway.

**Why:** Sends each request to the right model.

**Category:** Routing & gateways · **Stack layer:** runtime

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://oneapi.justsong.cn/
- Repo: https://github.com/songquanpeng/one-api
- README: https://github.com/songquanpeng/one-api#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "portkey-gateway"
name: "Portkey Gateway"
kind: "repo"
tier: "catalog"
category: "routing"
category_label: "Routing & gateways"
stack_layer: "runtime"
homepage: "https://portkey.ai/features/ai-gateway"
repo: "https://github.com/Portkey-AI/gateway"
license: "MIT"
stars: 13194
last_push: "2026-05-25"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Portkey Gateway

**What:** Fast AI gateway with guardrails and fallbacks.

**Why:** Sends each request to the right model.

**Category:** Routing & gateways · **Stack layer:** runtime

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
npx @portkey-ai/gateway
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://portkey.ai/features/ai-gateway
- Repo: https://github.com/Portkey-AI/gateway
- README: https://github.com/Portkey-AI/gateway#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "bifrost"
name: "Bifrost"
kind: "repo"
tier: "catalog"
category: "routing"
category_label: "Routing & gateways"
stack_layer: "runtime"
homepage: "https://www.getmaxim.ai/bifrost"
repo: "https://github.com/maximhq/bifrost"
license: "Apache-2.0"
stars: 8833
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Bifrost

**What:** High-performance LLM and MCP gateway.

**Why:** Sends each request to the right model.

**Category:** Routing & gateways · **Stack layer:** runtime

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
npx -y @maximhq/bifrost
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://www.getmaxim.ai/bifrost
- Repo: https://github.com/maximhq/bifrost
- README: https://github.com/maximhq/bifrost#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "plano"
name: "Plano"
kind: "repo"
tier: "catalog"
category: "routing"
category_label: "Routing & gateways"
stack_layer: "runtime"
homepage: "https://planoai.dev"
repo: "https://github.com/katanemo/plano"
license: "Apache-2.0"
stars: 7090
last_push: "2026-10-07"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Plano

**What:** AI-native proxy with smart LLM routing.

**Why:** Sends each request to the right model.

**Category:** Routing & gateways · **Stack layer:** runtime

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://planoai.dev
- Repo: https://github.com/katanemo/plano
- README: https://github.com/katanemo/plano#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "llmrouter"
name: "LLMRouter"
kind: "repo"
tier: "catalog"
category: "routing"
category_label: "Routing & gateways"
stack_layer: "runtime"
homepage: "https://ulab-uiuc.github.io/LLMRouter/"
repo: "https://github.com/ulab-uiuc/LLMRouter"
license: "MIT"
stars: 3006
last_push: "2026-10-09"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# LLMRouter

**What:** Research library of LLM routing methods.

**Why:** Sends each request to the right model.

**Category:** Routing & gateways · **Stack layer:** runtime

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install llmrouter-lib
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
pip uninstall -y llmrouter-lib
```

## Links

- Homepage: https://ulab-uiuc.github.io/LLMRouter/
- Repo: https://github.com/ulab-uiuc/LLMRouter
- README: https://github.com/ulab-uiuc/LLMRouter#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "envoy-ai-gateway"
name: "Envoy AI Gateway"
kind: "repo"
tier: "catalog"
category: "routing"
category_label: "Routing & gateways"
stack_layer: "runtime"
homepage: "https://theagentrouter.ai/"
repo: "https://github.com/theagentrouter/agent-router"
license: "Apache-2.0"
stars: 2229
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Envoy AI Gateway

**What:** Envoy-based gateway for generative AI services.

**Why:** Sends each request to the right model.

**Category:** Routing & gateways · **Stack layer:** runtime

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://theagentrouter.ai/
- Repo: https://github.com/theagentrouter/agent-router
- README: https://github.com/theagentrouter/agent-router#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "nvidia-llm-router"
name: "NVIDIA LLM Router"
kind: "repo"
tier: "catalog"
category: "routing"
category_label: "Routing & gateways"
stack_layer: "runtime"
homepage: "https://build.nvidia.com/nvidia/llm-router"
repo: "https://github.com/NVIDIA-AI-Blueprints/llm-router"
license: "Apache-2.0"
stars: 354
last_push: "2026-07-24"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# NVIDIA LLM Router

**What:** Routes each prompt to the best-fit model.

**Why:** Sends each request to the right model.

**Category:** Routing & gateways · **Stack layer:** runtime

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://build.nvidia.com/nvidia/llm-router
- Repo: https://github.com/NVIDIA-AI-Blueprints/llm-router
- README: https://github.com/NVIDIA-AI-Blueprints/llm-router#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "mcp-python-sdk"
name: "MCP Python SDK"
kind: "repo"
tier: "catalog"
category: "mcp"
category_label: "MCP servers & tools"
stack_layer: "tools"
homepage: "https://py.sdk.modelcontextprotocol.io/"
repo: "https://github.com/modelcontextprotocol/python-sdk"
license: "MIT"
stars: 24588
last_push: "2026-10-13"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# MCP Python SDK

**What:** Official Python SDK for MCP servers and clients.

**Why:** Gives the agent hands: web, files, apps.

**Category:** MCP servers & tools · **Stack layer:** tools

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
uv add "mcp[cli]"
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://py.sdk.modelcontextprotocol.io/
- Repo: https://github.com/modelcontextprotocol/python-sdk
- README: https://github.com/modelcontextprotocol/python-sdk#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "llm-cli"
name: "LLM CLI"
kind: "repo"
tier: "catalog"
category: "mcp"
category_label: "MCP servers & tools"
stack_layer: "tools"
homepage: "https://llm.datasette.io"
repo: "https://github.com/simonw/llm"
license: "Apache-2.0"
stars: 12624
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# LLM CLI

**What:** CLI and Python library for any LLM, local or cloud.

**Why:** Gives the agent hands: web, files, apps.

**Category:** MCP servers & tools · **Stack layer:** tools

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install llm
```

2. [macos] source: README (auto-extracted); status: unverified, not executed

```bash
brew install llm
```

3. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pipx install llm
```

4. [any] source: README (auto-extracted); status: unverified, not executed

```bash
uv tool install llm
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
pip uninstall -y llm
```

2. source: derived inverse of install command

```bash
brew uninstall llm
```

3. source: derived inverse of install command

```bash
pipx uninstall llm
```

4. source: derived inverse of install command

```bash
uv tool uninstall llm
```

## Links

- Homepage: https://llm.datasette.io
- Repo: https://github.com/simonw/llm
- README: https://github.com/simonw/llm#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "mcp-inspector"
name: "MCP Inspector"
kind: "repo"
tier: "catalog"
category: "mcp"
category_label: "MCP servers & tools"
stack_layer: "tools"
homepage: "https://modelcontextprotocol.io/docs/2026-07-28/tools/inspector"
repo: "https://github.com/modelcontextprotocol/inspector"
license: "Other"
stars: 11084
last_push: "2026-10-14"
archived: false
tags: ["license-unclear"]
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# MCP Inspector

**What:** Visual tester for MCP servers.

**Why:** Gives the agent hands: web, files, apps.

**Category:** MCP servers & tools · **Stack layer:** tools

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://modelcontextprotocol.io/docs/2026-07-28/tools/inspector
- Repo: https://github.com/modelcontextprotocol/inspector
- README: https://github.com/modelcontextprotocol/inspector#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "n8n"
name: "n8n"
kind: "repo"
tier: "catalog"
category: "mcp"
category_label: "MCP servers & tools"
stack_layer: "tools"
homepage: "https://n8n.io"
repo: "https://github.com/n8n-io/n8n"
license: "Other"
stars: 207507
last_push: "2026-10-15"
archived: false
tags: ["license-unclear"]
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# n8n

**What:** Workflow automation with AI nodes, self-hostable.

**Why:** Gives the agent hands: web, files, apps.

**Category:** MCP servers & tools · **Stack layer:** tools

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
curl -fsSL https://get.n8n.io | sh
```

2. [any] source: README (auto-extracted); status: unverified, not executed

```bash
docker run -it --rm --name n8n -p 5678:5678 -v n8n_data:/home/node/.n8n docker.n8n.io/n8nio/n8n
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
docker rm -f n8n
```

## Links

- Homepage: https://n8n.io
- Repo: https://github.com/n8n-io/n8n
- README: https://github.com/n8n-io/n8n#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "firecrawl"
name: "Firecrawl"
kind: "repo"
tier: "catalog"
category: "mcp"
category_label: "MCP servers & tools"
stack_layer: "tools"
homepage: "https://firecrawl.dev"
repo: "https://github.com/firecrawl/firecrawl"
license: "AGPL-3.0"
stars: 191861
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Firecrawl

**What:** Turn websites into LLM-ready data.

**Why:** Gives the agent hands: web, files, apps.

**Category:** MCP servers & tools · **Stack layer:** tools

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://firecrawl.dev
- Repo: https://github.com/firecrawl/firecrawl
- README: https://github.com/firecrawl/firecrawl#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "awesome-mcp-servers"
name: "Awesome MCP Servers"
kind: "repo"
tier: "catalog"
category: "mcp"
category_label: "MCP servers & tools"
stack_layer: "tools"
homepage: "https://glama.ai/mcp/servers"
repo: "https://github.com/punkpeye/awesome-mcp-servers"
license: "MIT"
stars: 96394
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Awesome MCP Servers

**What:** Big curated list of MCP servers.

**Why:** Gives the agent hands: web, files, apps.

**Category:** MCP servers & tools · **Stack layer:** tools

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://glama.ai/mcp/servers
- Repo: https://github.com/punkpeye/awesome-mcp-servers
- README: https://github.com/punkpeye/awesome-mcp-servers#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "crawl4ai"
name: "Crawl4AI"
kind: "repo"
tier: "catalog"
category: "mcp"
category_label: "MCP servers & tools"
stack_layer: "tools"
homepage: "https://crawl4ai.com"
repo: "https://github.com/unclecode/crawl4ai"
license: "Apache-2.0"
stars: 85617
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Crawl4AI

**What:** Open-source crawler that outputs clean markdown.

**Why:** Gives the agent hands: web, files, apps.

**Category:** MCP servers & tools · **Stack layer:** tools

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install -U crawl4ai
```

2. [any] source: README (auto-extracted); status: unverified, not executed

```bash
git clone https://github.com/unclecode/crawl4ai.git
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
pip uninstall -y crawl4ai
```

2. source: derived inverse of install command

```bash
rm -rf crawl4ai
```

## Links

- Homepage: https://crawl4ai.com
- Repo: https://github.com/unclecode/crawl4ai
- README: https://github.com/unclecode/crawl4ai#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "context7"
name: "Context7"
kind: "repo"
tier: "catalog"
category: "mcp"
category_label: "MCP servers & tools"
stack_layer: "tools"
homepage: "https://context7.com"
repo: "https://github.com/upstash/context7"
license: "MIT"
stars: 63091
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Context7

**What:** Up-to-date library docs for coding agents.

**Why:** Gives the agent hands: web, files, apps.

**Category:** MCP servers & tools · **Stack layer:** tools

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
npx ctx7 setup
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://context7.com
- Repo: https://github.com/upstash/context7
- README: https://github.com/upstash/context7#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "chrome-devtools-mcp"
name: "Chrome DevTools MCP"
kind: "repo"
tier: "catalog"
category: "mcp"
category_label: "MCP servers & tools"
stack_layer: "tools"
homepage: "https://developer.chrome.com/docs/devtools/agents"
repo: "https://github.com/ChromeDevTools/chrome-devtools-mcp"
license: "Apache-2.0"
stars: 53597
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Chrome DevTools MCP

**What:** Chrome DevTools as an MCP server.

**Why:** Gives the agent hands: web, files, apps.

**Category:** MCP servers & tools · **Stack layer:** tools

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://developer.chrome.com/docs/devtools/agents
- Repo: https://github.com/ChromeDevTools/chrome-devtools-mcp
- README: https://github.com/ChromeDevTools/chrome-devtools-mcp#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "searxng"
name: "SearXNG"
kind: "repo"
tier: "catalog"
category: "mcp"
category_label: "MCP servers & tools"
stack_layer: "tools"
homepage: "https://docs.searxng.org"
repo: "https://github.com/searxng/searxng"
license: "AGPL-3.0"
stars: 38438
last_push: "2026-10-14"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# SearXNG

**What:** Self-hosted private metasearch engine.

**Why:** Gives the agent hands: web, files, apps.

**Category:** MCP servers & tools · **Stack layer:** tools

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://docs.searxng.org
- Repo: https://github.com/searxng/searxng
- README: https://github.com/searxng/searxng#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "playwright-mcp"
name: "Playwright MCP"
kind: "repo"
tier: "catalog"
category: "mcp"
category_label: "MCP servers & tools"
stack_layer: "tools"
homepage: "https://www.npmjs.com/package/@playwright/mcp"
repo: "https://github.com/microsoft/playwright-mcp"
license: "Apache-2.0"
stars: 38199
last_push: "2026-10-08"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Playwright MCP

**What:** Browser automation MCP server.

**Why:** Gives the agent hands: web, files, apps.

**Category:** MCP servers & tools · **Stack layer:** tools

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://www.npmjs.com/package/@playwright/mcp
- Repo: https://github.com/microsoft/playwright-mcp
- README: https://github.com/microsoft/playwright-mcp#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "github-mcp-server"
name: "GitHub MCP Server"
kind: "repo"
tier: "catalog"
category: "mcp"
category_label: "MCP servers & tools"
stack_layer: "tools"
homepage: null
repo: "https://github.com/github/github-mcp-server"
license: "MIT"
stars: 33645
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# GitHub MCP Server

**What:** GitHub's official MCP server.

**Why:** Gives the agent hands: web, files, apps.

**Category:** MCP servers & tools · **Stack layer:** tools

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Repo: https://github.com/github/github-mcp-server
- README: https://github.com/github/github-mcp-server#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "serena"
name: "Serena"
kind: "repo"
tier: "catalog"
category: "mcp"
category_label: "MCP servers & tools"
stack_layer: "tools"
homepage: "https://oraios.github.io/serena"
repo: "https://github.com/oraios/serena"
license: "Other"
stars: 30291
last_push: "2026-10-15"
archived: false
tags: ["license-unclear"]
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Serena

**What:** Semantic code retrieval and editing over MCP.

**Why:** Gives the agent hands: web, files, apps.

**Category:** MCP servers & tools · **Stack layer:** tools

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
uv tool install -p 3.13 serena-agent
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
uv tool uninstall serena-agent
```

## Links

- Homepage: https://oraios.github.io/serena
- Repo: https://github.com/oraios/serena
- README: https://github.com/oraios/serena#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "nextchat"
name: "NextChat"
kind: "repo"
tier: "catalog"
category: "ui"
category_label: "Chat UIs & front-ends"
stack_layer: "harness"
homepage: "https://nextchat.club"
repo: "https://github.com/ChatGPTNextWeb/NextChat"
license: "MIT"
stars: 88853
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# NextChat

**What:** Lightweight cross-platform chat client.

**Why:** A friendly window onto your local models.

**Category:** Chat UIs & front-ends · **Stack layer:** harness

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://nextchat.club
- Repo: https://github.com/ChatGPTNextWeb/NextChat
- README: https://github.com/ChatGPTNextWeb/NextChat#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "lobechat"
name: "LobeChat"
kind: "repo"
tier: "catalog"
category: "ui"
category_label: "Chat UIs & front-ends"
stack_layer: "harness"
homepage: "https://lobehub.com"
repo: "https://github.com/lobehub/lobehub"
license: "Other"
stars: 83250
last_push: "2026-10-15"
archived: false
tags: ["license-unclear"]
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# LobeChat

**What:** Agent workspace and chat UI.

**Why:** A friendly window onto your local models.

**Category:** Chat UIs & front-ends · **Stack layer:** harness

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://lobehub.com
- Repo: https://github.com/lobehub/lobehub
- README: https://github.com/lobehub/lobehub#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "cherry-studio"
name: "Cherry Studio"
kind: "repo"
tier: "catalog"
category: "ui"
category_label: "Chat UIs & front-ends"
stack_layer: "harness"
homepage: "https://cherryai.com"
repo: "https://github.com/CherryHQ/cherry-studio"
license: "AGPL-3.0"
stars: 52668
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Cherry Studio

**What:** Desktop AI studio for many providers.

**Why:** A friendly window onto your local models.

**Category:** Chat UIs & front-ends · **Stack layer:** harness

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://cherryai.com
- Repo: https://github.com/CherryHQ/cherry-studio
- README: https://github.com/CherryHQ/cherry-studio#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "text-generation-webui"
name: "text-generation-webui"
kind: "repo"
tier: "catalog"
category: "ui"
category_label: "Chat UIs & front-ends"
stack_layer: "harness"
homepage: null
repo: "https://github.com/oobabooga/textgen"
license: "AGPL-3.0"
stars: 47730
last_push: "2026-08-17"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# text-generation-webui

**What:** Desktop app for local LLMs (text-generation-webui).

**Why:** A friendly window onto your local models.

**Category:** Chat UIs & front-ends · **Stack layer:** harness

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
conda install -y -c "nvidia/label/cuda-12.8.1" cuda
```

2. [any] source: README (auto-extracted); status: unverified, not executed

```bash
git clone https://github.com/oobabooga/textgen
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
rm -rf textgen
```

## Links

- Repo: https://github.com/oobabooga/textgen
- README: https://github.com/oobabooga/textgen#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "librechat"
name: "LibreChat"
kind: "repo"
tier: "catalog"
category: "ui"
category_label: "Chat UIs & front-ends"
stack_layer: "harness"
homepage: "https://librechat.ai/"
repo: "https://github.com/LibreChat-AI/LibreChat"
license: "MIT"
stars: 45756
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# LibreChat

**What:** Self-hosted multi-provider ChatGPT clone.

**Why:** A friendly window onto your local models.

**Category:** Chat UIs & front-ends · **Stack layer:** harness

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://librechat.ai/
- Repo: https://github.com/LibreChat-AI/LibreChat
- README: https://github.com/LibreChat-AI/LibreChat#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "jan"
name: "Jan"
kind: "repo"
tier: "catalog"
category: "ui"
category_label: "Chat UIs & front-ends"
stack_layer: "harness"
homepage: "https://jan.ai/"
repo: "https://github.com/janhq/jan"
license: "Other"
stars: 44958
last_push: "2026-10-15"
archived: false
tags: ["license-unclear"]
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Jan

**What:** Offline ChatGPT alternative for your desktop.

**Why:** A friendly window onto your local models.

**Category:** Chat UIs & front-ends · **Stack layer:** harness

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
git clone https://github.com/janhq/jan
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
rm -rf jan
```

## Links

- Homepage: https://jan.ai/
- Repo: https://github.com/janhq/jan
- README: https://github.com/janhq/jan#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "chatbox"
name: "Chatbox"
kind: "repo"
tier: "catalog"
category: "ui"
category_label: "Chat UIs & front-ends"
stack_layer: "harness"
homepage: "https://chatboxai.app?utm_medium=github"
repo: "https://github.com/chatboxai/chatbox"
license: "GPL-3.0"
stars: 42028
last_push: "2026-09-24"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Chatbox

**What:** Desktop and mobile AI client.

**Why:** A friendly window onto your local models.

**Category:** Chat UIs & front-ends · **Stack layer:** harness

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
git clone https://github.com/chatboxai/chatbox.git
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
rm -rf chatbox
```

## Links

- Homepage: https://chatboxai.app?utm_medium=github
- Repo: https://github.com/chatboxai/chatbox
- README: https://github.com/chatboxai/chatbox#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "sillytavern"
name: "SillyTavern"
kind: "repo"
tier: "catalog"
category: "ui"
category_label: "Chat UIs & front-ends"
stack_layer: "harness"
homepage: "https://sillytavern.app"
repo: "https://github.com/SillyTavern/SillyTavern"
license: "AGPL-3.0"
stars: 34522
last_push: "2026-10-02"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# SillyTavern

**What:** Power-user chat and roleplay front-end.

**Why:** A friendly window onto your local models.

**Category:** Chat UIs & front-ends · **Stack layer:** harness

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://sillytavern.app
- Repo: https://github.com/SillyTavern/SillyTavern
- README: https://github.com/SillyTavern/SillyTavern#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "open-llm-vtuber"
name: "Open-LLM-VTuber"
kind: "repo"
tier: "catalog"
category: "ui"
category_label: "Chat UIs & front-ends"
stack_layer: "harness"
homepage: "https://open-llm-vtuber.github.io/"
repo: "https://github.com/Open-LLM-VTuber/Open-LLM-VTuber"
license: "Other"
stars: 14115
last_push: "2026-05-15"
archived: false
tags: ["license-unclear"]
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Open-LLM-VTuber

**What:** Voice chat with an animated avatar, locally.

**Why:** A friendly window onto your local models.

**Category:** Chat UIs & front-ends · **Stack layer:** harness

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://open-llm-vtuber.github.io/
- Repo: https://github.com/Open-LLM-VTuber/Open-LLM-VTuber
- README: https://github.com/Open-LLM-VTuber/Open-LLM-VTuber#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "hf-chat-ui"
name: "HF Chat UI"
kind: "repo"
tier: "catalog"
category: "ui"
category_label: "Chat UIs & front-ends"
stack_layer: "harness"
homepage: "https://huggingface.co/chat"
repo: "https://github.com/huggingface/chat-ui"
license: "Apache-2.0"
stars: 10985
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# HF Chat UI

**What:** The open code behind HuggingChat.

**Why:** A friendly window onto your local models.

**Category:** Chat UIs & front-ends · **Stack layer:** harness

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
git clone https://github.com/huggingface/chat-ui
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
rm -rf chat-ui
```

## Links

- Homepage: https://huggingface.co/chat
- Repo: https://github.com/huggingface/chat-ui
- README: https://github.com/huggingface/chat-ui#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "big-agi"
name: "big-AGI"
kind: "repo"
tier: "catalog"
category: "ui"
category_label: "Chat UIs & front-ends"
stack_layer: "harness"
homepage: "https://big-agi.com"
repo: "https://github.com/enricoros/big-AGI"
license: "MIT"
stars: 7146
last_push: "2026-10-13"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# big-AGI

**What:** Advanced multi-model chat suite.

**Why:** A friendly window onto your local models.

**Category:** Chat UIs & front-ends · **Stack layer:** harness

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://big-agi.com
- Repo: https://github.com/enricoros/big-AGI
- README: https://github.com/enricoros/big-AGI#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "enchanted"
name: "Enchanted"
kind: "repo"
tier: "catalog"
category: "ui"
category_label: "Chat UIs & front-ends"
stack_layer: "harness"
homepage: null
repo: "https://github.com/gluonfield/enchanted"
license: "Apache-2.0"
stars: 6008
last_push: "2026-07-07"
archived: false
tags: ["apple-silicon"]
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Enchanted

**What:** Native macOS/iOS app for self-hosted models.

**Why:** A friendly window onto your local models.

**Category:** Chat UIs & front-ends · **Stack layer:** harness

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Repo: https://github.com/gluonfield/enchanted
- README: https://github.com/gluonfield/enchanted#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "llama-vscode"
name: "llama.vscode"
kind: "repo"
tier: "catalog"
category: "ui"
category_label: "Chat UIs & front-ends"
stack_layer: "harness"
homepage: null
repo: "https://github.com/ggml-org/llama.vscode"
license: "MIT"
stars: 1537
last_push: "2026-10-10"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# llama.vscode

**What:** Local code completion in VS Code via llama.cpp.

**Why:** A friendly window onto your local models.

**Category:** Chat UIs & front-ends · **Stack layer:** harness

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Repo: https://github.com/ggml-org/llama.vscode
- README: https://github.com/ggml-org/llama.vscode#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "mlx-audio"
name: "MLX-Audio"
kind: "repo"
tier: "catalog"
category: "voice"
category_label: "Voice: speech-to-text & TTS"
stack_layer: "tools"
homepage: "https://blaizzy.github.io/mlx-audio/"
repo: "https://github.com/Blaizzy/mlx-audio"
license: "MIT"
stars: 8049
last_push: "2026-10-14"
archived: false
tags: ["apple-silicon"]
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# MLX-Audio

**What:** TTS, STT and speech-to-speech on MLX.

**Why:** Talk to it and hear it answer, offline.

**Category:** Voice: speech-to-text & TTS · **Stack layer:** tools

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
uv tool install --force mlx-audio --prerelease=allow
```

2. [any] source: README (auto-extracted); status: unverified, not executed

```bash
uv tool install --force git+https://github.com/Blaizzy/mlx-audio.git --prerelease=allow
```

3. [any] source: README (auto-extracted); status: unverified, not executed

```bash
npm install && npm run dev
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
uv tool uninstall mlx-audio
```

## Links

- Homepage: https://blaizzy.github.io/mlx-audio/
- Repo: https://github.com/Blaizzy/mlx-audio
- README: https://github.com/Blaizzy/mlx-audio#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "whisperkit"
name: "WhisperKit"
kind: "repo"
tier: "catalog"
category: "voice"
category_label: "Voice: speech-to-text & TTS"
stack_layer: "tools"
homepage: null
repo: "https://github.com/argmaxinc/argmax-oss-swift"
license: "MIT"
stars: 6404
last_push: "2026-10-11"
archived: false
tags: ["apple-silicon"]
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# WhisperKit

**What:** On-device speech AI for Apple Silicon (WhisperKit).

**Why:** Talk to it and hear it answer, offline.

**Category:** Voice: speech-to-text & TTS · **Stack layer:** tools

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Repo: https://github.com/argmaxinc/argmax-oss-swift
- README: https://github.com/argmaxinc/argmax-oss-swift#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "parakeet-mlx"
name: "Parakeet MLX"
kind: "repo"
tier: "catalog"
category: "voice"
category_label: "Voice: speech-to-text & TTS"
stack_layer: "tools"
homepage: null
repo: "https://github.com/senstella/parakeet-mlx"
license: "Apache-2.0"
stars: 987
last_push: "2026-10-01"
archived: false
tags: ["apple-silicon"]
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Parakeet MLX

**What:** NVIDIA Parakeet speech recognition on MLX.

**Why:** Talk to it and hear it answer, offline.

**Category:** Voice: speech-to-text & TTS · **Stack layer:** tools

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
uv add parakeet-mlx -U
```

2. [any] source: README (auto-extracted); status: unverified, not executed

```bash
uv tool install parakeet-mlx -U
```

3. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install parakeet-mlx -U
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
uv tool uninstall parakeet-mlx
```

2. source: derived inverse of install command

```bash
pip uninstall -y parakeet-mlx
```

## Links

- Repo: https://github.com/senstella/parakeet-mlx
- README: https://github.com/senstella/parakeet-mlx#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "whisper"
name: "Whisper"
kind: "repo"
tier: "catalog"
category: "voice"
category_label: "Voice: speech-to-text & TTS"
stack_layer: "tools"
homepage: null
repo: "https://github.com/openai/whisper"
license: "MIT"
stars: 110561
last_push: "2026-08-31"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Whisper

**What:** OpenAI's original speech recognition model.

**Why:** Talk to it and hear it answer, offline.

**Category:** Voice: speech-to-text & TTS · **Stack layer:** tools

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Repo: https://github.com/openai/whisper
- README: https://github.com/openai/whisper#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "chattts"
name: "ChatTTS"
kind: "repo"
tier: "catalog"
category: "voice"
category_label: "Voice: speech-to-text & TTS"
stack_layer: "tools"
homepage: "https://2noise.com"
repo: "https://github.com/2noise/ChatTTS"
license: "AGPL-3.0"
stars: 39909
last_push: "2026-04-10"
archived: false
tags: ["slow-activity"]
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# ChatTTS

**What:** Conversational text-to-speech model.

**Why:** Talk to it and hear it answer, offline.

**Category:** Voice: speech-to-text & TTS · **Stack layer:** tools

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install --upgrade -r requirements.txt
```

2. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install safetensors vllm==0.2.7 torchaudio
```

3. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install git+https://github.com/NVIDIA/TransformerEngine.git@stable
```

4. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install flash-attn --no-build-isolation
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
pip uninstall -y requirements.txt
```

2. source: derived inverse of install command

```bash
pip uninstall -y safetensors
```

3. source: derived inverse of install command

```bash
pip uninstall -y flash-attn
```

## Links

- Homepage: https://2noise.com
- Repo: https://github.com/2noise/ChatTTS
- README: https://github.com/2noise/ChatTTS#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "handy"
name: "Handy"
kind: "repo"
tier: "catalog"
category: "voice"
category_label: "Voice: speech-to-text & TTS"
stack_layer: "tools"
homepage: "https://handy.computer"
repo: "https://github.com/cjpais/Handy"
license: "MIT"
stars: 33870
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Handy

**What:** Offline push-to-talk dictation app.

**Why:** Talk to it and hear it answer, offline.

**Category:** Voice: speech-to-text & TTS · **Stack layer:** tools

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://handy.computer
- Repo: https://github.com/cjpais/Handy
- README: https://github.com/cjpais/Handy#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "fish-speech"
name: "Fish Speech"
kind: "repo"
tier: "catalog"
category: "voice"
category_label: "Voice: speech-to-text & TTS"
stack_layer: "tools"
homepage: "https://speech.fish.audio"
repo: "https://github.com/fishaudio/fish-speech"
license: "Other"
stars: 33167
last_push: "2026-10-14"
archived: false
tags: ["license-unclear"]
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Fish Speech

**What:** Open-source text-to-speech with voice cloning.

**Why:** Talk to it and hear it answer, offline.

**Category:** Voice: speech-to-text & TTS · **Stack layer:** tools

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://speech.fish.audio
- Repo: https://github.com/fishaudio/fish-speech
- README: https://github.com/fishaudio/fish-speech#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "chatterbox"
name: "Chatterbox"
kind: "repo"
tier: "catalog"
category: "voice"
category_label: "Voice: speech-to-text & TTS"
stack_layer: "tools"
homepage: "https://resemble-ai.github.io/chatterbox_demopage/"
repo: "https://github.com/resemble-ai/chatterbox"
license: "MIT"
stars: 26965
last_push: "2026-07-21"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Chatterbox

**What:** Open-source expressive TTS.

**Why:** Talk to it and hear it answer, offline.

**Category:** Voice: speech-to-text & TTS · **Stack layer:** tools

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install chatterbox-tts
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
pip uninstall -y chatterbox-tts
```

## Links

- Homepage: https://resemble-ai.github.io/chatterbox_demopage/
- Repo: https://github.com/resemble-ai/chatterbox
- README: https://github.com/resemble-ai/chatterbox#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "faster-whisper"
name: "faster-whisper"
kind: "repo"
tier: "catalog"
category: "voice"
category_label: "Voice: speech-to-text & TTS"
stack_layer: "tools"
homepage: null
repo: "https://github.com/SYSTRAN/faster-whisper"
license: "MIT"
stars: 25876
last_push: "2026-10-13"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# faster-whisper

**What:** Whisper transcription, faster, via CTranslate2.

**Why:** Talk to it and hear it answer, offline.

**Category:** Voice: speech-to-text & TTS · **Stack layer:** tools

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install nvidia-cublas-cu12 nvidia-cudnn-cu12==9.*
```

2. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install faster-whisper
```

3. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install --force-reinstall "faster-whisper @ https://github.com/SYSTRAN/faster-whisper/archive/refs/heads/master.tar.gz"
```

4. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install --force-reinstall "faster-whisper @ https://github.com/SYSTRAN/faster-whisper/archive/a4f1cc8f11433e454c3934442b5e1a4ed5e865c3.tar.gz"
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
pip uninstall -y nvidia-cublas-cu12
```

2. source: derived inverse of install command

```bash
pip uninstall -y faster-whisper
```

## Links

- Repo: https://github.com/SYSTRAN/faster-whisper
- README: https://github.com/SYSTRAN/faster-whisper#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "whisperx"
name: "WhisperX"
kind: "repo"
tier: "catalog"
category: "voice"
category_label: "Voice: speech-to-text & TTS"
stack_layer: "tools"
homepage: null
repo: "https://github.com/m-bain/whisperX"
license: "BSD-2-Clause"
stars: 24579
last_push: "2026-09-26"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# WhisperX

**What:** Whisper with word timestamps and speaker labels.

**Why:** Talk to it and hear it answer, offline.

**Category:** Voice: speech-to-text & TTS · **Stack layer:** tools

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install whisperx
```

2. [any] source: README (auto-extracted); status: unverified, not executed

```bash
uvx whisperx
```

3. [any] source: README (auto-extracted); status: unverified, not executed

```bash
uvx git+https://github.com/m-bain/whisperX.git
```

4. [any] source: README (auto-extracted); status: unverified, not executed

```bash
git clone https://github.com/m-bain/whisperX.git
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
pip uninstall -y whisperx
```

2. source: derived inverse of install command

```bash
rm -rf whisperX
```

## Links

- Repo: https://github.com/m-bain/whisperX
- README: https://github.com/m-bain/whisperX#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "cosyvoice"
name: "CosyVoice"
kind: "repo"
tier: "catalog"
category: "voice"
category_label: "Voice: speech-to-text & TTS"
stack_layer: "tools"
homepage: "https://funaudiollm.github.io/cosyvoice3"
repo: "https://github.com/QwenAudio/CosyVoice"
license: "Apache-2.0"
stars: 23997
last_push: "2026-05-25"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# CosyVoice

**What:** Multilingual voice generation model.

**Why:** Talk to it and hear it answer, offline.

**Category:** Voice: speech-to-text & TTS · **Stack layer:** tools

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
git clone --recursive https://github.com/FunAudioLLM/CosyVoice.git
```

2. [any] source: README (auto-extracted); status: unverified, not executed

```bash
docker run -d --runtime=nvidia -p 50000:50000 cosyvoice:v1.0 /bin/bash -c "cd /opt/CosyVoice/CosyVoice/runtime/python/grpc && python3 server.py --port 50000 --max_conc 4 --model_dir iic/CosyVoice-300M && sleep infinity"
```

3. [any] source: README (auto-extracted); status: unverified, not executed

```bash
docker run -d --runtime=nvidia -p 50000:50000 cosyvoice:v1.0 /bin/bash -c "cd /opt/CosyVoice/CosyVoice/runtime/python/fastapi && python3 server.py --port 50000 --model_dir iic/CosyVoice-300M && sleep infinity"
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
rm -rf CosyVoice
```

## Links

- Homepage: https://funaudiollm.github.io/cosyvoice3
- Repo: https://github.com/QwenAudio/CosyVoice
- README: https://github.com/QwenAudio/CosyVoice#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "dia"
name: "Dia"
kind: "repo"
tier: "catalog"
category: "voice"
category_label: "Voice: speech-to-text & TTS"
stack_layer: "tools"
homepage: null
repo: "https://github.com/nari-labs/dia"
license: "Apache-2.0"
stars: 19407
last_push: "2025-11-19"
archived: false
tags: ["slow-activity"]
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Dia

**What:** TTS that generates realistic dialogue.

**Why:** Talk to it and hear it answer, offline.

**Category:** Voice: speech-to-text & TTS · **Stack layer:** tools

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
uv pip install git+https://github.com/huggingface/transformers.git
```

2. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install git+https://github.com/nari-labs/dia.git
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Repo: https://github.com/nari-labs/dia
- README: https://github.com/nari-labs/dia#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "nemo-parakeet"
name: "NeMo (Parakeet)"
kind: "repo"
tier: "catalog"
category: "voice"
category_label: "Voice: speech-to-text & TTS"
stack_layer: "tools"
homepage: "https://docs.nvidia.com/nemo/speech/nightly/index.html"
repo: "https://github.com/NVIDIA-NeMo/Speech"
license: "Apache-2.0"
stars: 18585
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# NeMo (Parakeet)

**What:** NVIDIA NeMo speech models (incl. Parakeet).

**Why:** Talk to it and hear it answer, offline.

**Category:** Voice: speech-to-text & TTS · **Stack layer:** tools

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://docs.nvidia.com/nemo/speech/nightly/index.html
- Repo: https://github.com/NVIDIA-NeMo/Speech
- README: https://github.com/NVIDIA-NeMo/Speech#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "stable-diffusion-cpp"
name: "stable-diffusion.cpp"
kind: "repo"
tier: "catalog"
category: "image"
category_label: "Image & video generation"
stack_layer: "tools"
homepage: null
repo: "https://github.com/leejet/stable-diffusion.cpp"
license: "MIT"
stars: 7692
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# stable-diffusion.cpp

**What:** Image and video diffusion in pure C/C++.

**Why:** Make images and video on your own machine.

**Category:** Image & video generation · **Stack layer:** tools

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Repo: https://github.com/leejet/stable-diffusion.cpp
- README: https://github.com/leejet/stable-diffusion.cpp#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "mflux"
name: "mflux"
kind: "repo"
tier: "catalog"
category: "image"
category_label: "Image & video generation"
stack_layer: "tools"
homepage: null
repo: "https://github.com/mflux-community/mflux"
license: "MIT"
stars: 2486
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# mflux

**What:** MLX-native image and video models for Mac.

**Why:** Make images and video on your own machine.

**Category:** Image & video generation · **Stack layer:** tools

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
uv tool install --upgrade mflux
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
uv tool uninstall mflux
```

## Links

- Repo: https://github.com/mflux-community/mflux
- README: https://github.com/mflux-community/mflux#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "qwen-image-2-1"
name: "Qwen-Image 2.1"
kind: "repo"
tier: "catalog"
category: "image"
category_label: "Image & video generation"
stack_layer: "tools"
homepage: null
repo: "https://github.com/QwenLM/Qwen-Image-2.1"
license: "Other"
stars: 1947
last_push: "2026-10-14"
archived: false
tags: ["license-unclear"]
seen_in_videos: ["SE_nPi7eeyI"]
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Qwen-Image 2.1

**What:** Qwen's open image generation and editing model.

**Why:** Make images and video on your own machine.

**Category:** Image & video generation · **Stack layer:** tools

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Repo: https://github.com/QwenLM/Qwen-Image-2.1
- README: https://github.com/QwenLM/Qwen-Image-2.1#readme
- Video: https://www.youtube.com/watch?v=SE_nPi7eeyI


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "draw-things"
name: "Draw Things"
kind: "repo"
tier: "catalog"
category: "image"
category_label: "Image & video generation"
stack_layer: "tools"
homepage: "https://drawthings.ai"
repo: "https://github.com/drawthingsai/draw-things-community"
license: "GPL-3.0"
stars: 588
last_push: "2026-10-15"
archived: false
tags: ["apple-silicon"]
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Draw Things

**What:** Community repo for the Draw Things Mac/iOS app.

**Why:** Make images and video on your own machine.

**Category:** Image & video generation · **Stack layer:** tools

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [macos] source: README (auto-extracted); status: unverified, not executed

```bash
brew install --HEAD drawthingsai/draw-things/draw-things-cli
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
brew uninstall --HEAD
```

## Links

- Homepage: https://drawthings.ai
- Repo: https://github.com/drawthingsai/draw-things-community
- README: https://github.com/drawthingsai/draw-things-community#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "stable-diffusion-webui"
name: "Stable Diffusion WebUI"
kind: "repo"
tier: "catalog"
category: "image"
category_label: "Image & video generation"
stack_layer: "tools"
homepage: null
repo: "https://github.com/AUTOMATIC1111/stable-diffusion-webui"
license: "AGPL-3.0"
stars: 165059
last_push: "2026-03-02"
archived: false
tags: ["slow-activity"]
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Stable Diffusion WebUI

**What:** The classic Stable Diffusion web UI.

**Why:** Make images and video on your own machine.

**Category:** Image & video generation · **Stack layer:** tools

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Repo: https://github.com/AUTOMATIC1111/stable-diffusion-webui
- README: https://github.com/AUTOMATIC1111/stable-diffusion-webui#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "comfyui"
name: "ComfyUI"
kind: "repo"
tier: "catalog"
category: "image"
category_label: "Image & video generation"
stack_layer: "tools"
homepage: "https://www.comfy.org/"
repo: "https://github.com/Comfy-Org/ComfyUI"
license: "GPL-3.0"
stars: 137692
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# ComfyUI

**What:** Node-based GUI and backend for diffusion models.

**Why:** Make images and video on your own machine.

**Category:** Image & video generation · **Stack layer:** tools

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install comfy-cli
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
pip uninstall -y comfy-cli
```

## Links

- Homepage: https://www.comfy.org/
- Repo: https://github.com/Comfy-Org/ComfyUI
- README: https://github.com/Comfy-Org/ComfyUI#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "fooocus"
name: "Fooocus"
kind: "repo"
tier: "catalog"
category: "image"
category_label: "Image & video generation"
stack_layer: "tools"
homepage: null
repo: "https://github.com/lllyasviel/Fooocus"
license: "GPL-3.0"
stars: 53435
last_push: "2025-12-01"
archived: false
tags: ["slow-activity"]
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Fooocus

**What:** Prompt-first, low-setup image generator.

**Why:** Make images and video on your own machine.

**Category:** Image & video generation · **Stack layer:** tools

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Repo: https://github.com/lllyasviel/Fooocus
- README: https://github.com/lllyasviel/Fooocus#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "diffusers"
name: "Diffusers"
kind: "repo"
tier: "catalog"
category: "image"
category_label: "Image & video generation"
stack_layer: "tools"
homepage: "https://huggingface.co/docs/diffusers"
repo: "https://github.com/huggingface/diffusers"
license: "Apache-2.0"
stars: 34726
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Diffusers

**What:** PyTorch library for image, video and audio diffusion.

**Why:** Make images and video on your own machine.

**Category:** Image & video generation · **Stack layer:** tools

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://huggingface.co/docs/diffusers
- Repo: https://github.com/huggingface/diffusers
- README: https://github.com/huggingface/diffusers#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "open-sora"
name: "Open-Sora"
kind: "repo"
tier: "catalog"
category: "image"
category_label: "Image & video generation"
stack_layer: "tools"
homepage: "https://hpcaitech.github.io/Open-Sora/"
repo: "https://github.com/hpcaitech/Open-Sora"
license: "Apache-2.0"
stars: 29873
last_push: "2026-04-09"
archived: false
tags: ["slow-activity"]
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Open-Sora

**What:** Open video generation models.

**Why:** Make images and video on your own machine.

**Category:** Image & video generation · **Stack layer:** tools

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://hpcaitech.github.io/Open-Sora/
- Repo: https://github.com/hpcaitech/Open-Sora
- README: https://github.com/hpcaitech/Open-Sora#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "invokeai"
name: "InvokeAI"
kind: "repo"
tier: "catalog"
category: "image"
category_label: "Image & video generation"
stack_layer: "tools"
homepage: "https://invoke-ai.github.io/InvokeAI/"
repo: "https://github.com/invoke-ai/InvokeAI"
license: "Apache-2.0"
stars: 28659
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# InvokeAI

**What:** Professional creative studio for diffusion.

**Why:** Make images and video on your own machine.

**Category:** Image & video generation · **Stack layer:** tools

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://invoke-ai.github.io/InvokeAI/
- Repo: https://github.com/invoke-ai/InvokeAI
- README: https://github.com/invoke-ai/InvokeAI#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "core-ml-stable-diffusion"
name: "Core ML Stable Diffusion"
kind: "repo"
tier: "catalog"
category: "image"
category_label: "Image & video generation"
stack_layer: "tools"
homepage: null
repo: "https://github.com/apple-aiml-research/ml-stable-diffusion"
license: "MIT"
stars: 17965
last_push: "2026-09-11"
archived: false
tags: ["apple-silicon"]
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Core ML Stable Diffusion

**What:** Stable Diffusion on Core ML for Apple Silicon.

**Why:** Make images and video on your own machine.

**Category:** Image & video generation · **Stack layer:** tools

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Repo: https://github.com/apple-aiml-research/ml-stable-diffusion
- README: https://github.com/apple-aiml-research/ml-stable-diffusion#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "wan-2-2"
name: "Wan 2.2"
kind: "repo"
tier: "catalog"
category: "image"
category_label: "Image & video generation"
stack_layer: "tools"
homepage: "https://wan.video"
repo: "https://github.com/Wan-Video/Wan2.2"
license: "Apache-2.0"
stars: 17950
last_push: "2026-09-21"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Wan 2.2

**What:** Open video generation models (Wan 2.2).

**Why:** Make images and video on your own machine.

**Category:** Image & video generation · **Stack layer:** tools

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
git clone https://github.com/Wan-Video/Wan2.2.git
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
rm -rf Wan2.2
```

## Links

- Homepage: https://wan.video
- Repo: https://github.com/Wan-Video/Wan2.2
- README: https://github.com/Wan-Video/Wan2.2#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "wan-2-1"
name: "Wan 2.1"
kind: "repo"
tier: "catalog"
category: "image"
category_label: "Image & video generation"
stack_layer: "tools"
homepage: "https://wan.video"
repo: "https://github.com/Wan-Video/Wan2.1"
license: "Apache-2.0"
stars: 17211
last_push: "2026-03-05"
archived: false
tags: ["slow-activity"]
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Wan 2.1

**What:** Open video generation models (Wan 2.1).

**Why:** Make images and video on your own machine.

**Category:** Image & video generation · **Stack layer:** tools

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
git clone https://github.com/Wan-Video/Wan2.1.git
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
rm -rf Wan2.1
```

## Links

- Homepage: https://wan.video
- Repo: https://github.com/Wan-Video/Wan2.1
- README: https://github.com/Wan-Video/Wan2.1#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "comfyui-manager"
name: "ComfyUI Manager"
kind: "repo"
tier: "catalog"
category: "image"
category_label: "Image & video generation"
stack_layer: "tools"
homepage: null
repo: "https://github.com/Comfy-Org/ComfyUI-Manager"
license: "GPL-3.0"
stars: 16467
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# ComfyUI Manager

**What:** Install and manage ComfyUI custom nodes.

**Why:** Make images and video on your own machine.

**Category:** Image & video generation · **Stack layer:** tools

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install comfy-cli
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
pip uninstall -y comfy-cli
```

## Links

- Repo: https://github.com/Comfy-Org/ComfyUI-Manager
- README: https://github.com/Comfy-Org/ComfyUI-Manager#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "mlx-lm-lora"
name: "MLX-LM-LoRA"
kind: "repo"
tier: "catalog"
category: "finetune"
category_label: "Fine-tuning"
stack_layer: "model"
homepage: "https://goekdeniz-guelmez.github.io/mlx-lm-lora/"
repo: "https://github.com/Goekdeniz-Guelmez/mlx-lm-lora"
license: "Apache-2.0"
stars: 434
last_push: "2026-10-13"
archived: false
tags: ["apple-silicon"]
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# MLX-LM-LoRA

**What:** LoRA and full fine-tuning on MLX.

**Why:** Teach a model your data and style.

**Category:** Fine-tuning · **Stack layer:** model

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install -U mlx-lm-lora
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
pip uninstall -y mlx-lm-lora
```

## Links

- Homepage: https://goekdeniz-guelmez.github.io/mlx-lm-lora/
- Repo: https://github.com/Goekdeniz-Guelmez/mlx-lm-lora
- README: https://github.com/Goekdeniz-Guelmez/mlx-lm-lora#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "unsloth"
name: "Unsloth"
kind: "repo"
tier: "catalog"
category: "finetune"
category_label: "Fine-tuning"
stack_layer: "model"
homepage: "https://unsloth.ai/docs"
repo: "https://github.com/unslothai/unsloth"
license: "Apache-2.0"
stars: 78064
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Unsloth

**What:** Fast, low-memory fine-tuning with a local UI.

**Why:** Teach a model your data and style.

**Category:** Fine-tuning · **Stack layer:** model

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
git clone https://github.com/unslothai/unsloth
```

2. [any] source: README (auto-extracted); status: unverified, not executed

```bash
git clone https://github.com/unslothai/unsloth.git
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
rm -rf unsloth
```

## Links

- Homepage: https://unsloth.ai/docs
- Repo: https://github.com/unslothai/unsloth
- README: https://github.com/unslothai/unsloth#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "llama-factory"
name: "LLaMA-Factory"
kind: "repo"
tier: "catalog"
category: "finetune"
category_label: "Fine-tuning"
stack_layer: "model"
homepage: "https://llamafactory.readthedocs.io"
repo: "https://github.com/hiyouga/LlamaFactory"
license: "Apache-2.0"
stars: 75495
last_push: "2026-10-10"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# LLaMA-Factory

**What:** Fine-tune 100+ LLMs and VLMs from one tool.

**Why:** Teach a model your data and style.

**Category:** Fine-tuning · **Stack layer:** model

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
git clone --depth 1 https://github.com/hiyouga/LlamaFactory.git
```

2. [any] source: README (auto-extracted); status: unverified, not executed

```bash
docker run -it --rm --gpus=all --ipc=host hiyouga/llamafactory:latest
```

3. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu126
```

4. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install bitsandbytes
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
rm -rf https://github.com/hiyouga/LlamaFactory.git
```

2. source: derived inverse of install command

```bash
pip uninstall -y torch
```

3. source: derived inverse of install command

```bash
pip uninstall -y bitsandbytes
```

## Links

- Homepage: https://llamafactory.readthedocs.io
- Repo: https://github.com/hiyouga/LlamaFactory
- README: https://github.com/hiyouga/LlamaFactory#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "nanogpt"
name: "nanoGPT"
kind: "repo"
tier: "catalog"
category: "finetune"
category_label: "Fine-tuning"
stack_layer: "model"
homepage: null
repo: "https://github.com/karpathy/nanoGPT"
license: "MIT"
stars: 63835
last_push: "2025-11-12"
archived: false
tags: ["slow-activity"]
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# nanoGPT

**What:** The simplest repo to train small GPTs.

**Why:** Teach a model your data and style.

**Category:** Fine-tuning · **Stack layer:** model

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install torch numpy transformers datasets tiktoken wandb tqdm
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
pip uninstall -y torch
```

## Links

- Repo: https://github.com/karpathy/nanoGPT
- README: https://github.com/karpathy/nanoGPT#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "nanochat"
name: "nanochat"
kind: "repo"
tier: "catalog"
category: "finetune"
category_label: "Fine-tuning"
stack_layer: "model"
homepage: null
repo: "https://github.com/karpathy/nanochat"
license: "MIT"
stars: 58660
last_push: "2026-09-07"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# nanochat

**What:** Train a small ChatGPT end to end on a budget.

**Why:** Teach a model your data and style.

**Category:** Fine-tuning · **Stack layer:** model

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Repo: https://github.com/karpathy/nanochat
- README: https://github.com/karpathy/nanochat#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "open-r1"
name: "Open R1"
kind: "repo"
tier: "catalog"
category: "finetune"
category_label: "Fine-tuning"
stack_layer: "model"
homepage: null
repo: "https://github.com/huggingface/open-r1"
license: "Apache-2.0"
stars: 26481
last_push: "2026-10-02"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Open R1

**What:** Open reproduction of DeepSeek-R1 training.

**Why:** Teach a model your data and style.

**Category:** Fine-tuning · **Stack layer:** model

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
uv pip install vllm==0.8.5.post1
```

2. [any] source: README (auto-extracted); status: unverified, not executed

```bash
uv pip install setuptools && uv pip install flash-attn --no-build-isolation
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
uv pip uninstall vllm
```

2. source: derived inverse of install command

```bash
uv pip uninstall setuptools
```

## Links

- Repo: https://github.com/huggingface/open-r1
- README: https://github.com/huggingface/open-r1#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "verl"
name: "verl"
kind: "repo"
tier: "catalog"
category: "finetune"
category_label: "Fine-tuning"
stack_layer: "model"
homepage: "https://verl-project.github.io"
repo: "https://github.com/verl-project/verl"
license: "Apache-2.0"
stars: 23891
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# verl

**What:** Reinforcement-learning post-training framework.

**Why:** Teach a model your data and style.

**Category:** Fine-tuning · **Stack layer:** model

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://verl-project.github.io
- Repo: https://github.com/verl-project/verl
- README: https://github.com/verl-project/verl#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "peft"
name: "PEFT"
kind: "repo"
tier: "catalog"
category: "finetune"
category_label: "Fine-tuning"
stack_layer: "model"
homepage: "https://huggingface.co/docs/peft"
repo: "https://github.com/huggingface/peft"
license: "Apache-2.0"
stars: 21790
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# PEFT

**What:** LoRA and other parameter-efficient fine-tuning.

**Why:** Teach a model your data and style.

**Category:** Fine-tuning · **Stack layer:** model

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install peft
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
pip uninstall -y peft
```

## Links

- Homepage: https://huggingface.co/docs/peft
- Repo: https://github.com/huggingface/peft
- README: https://github.com/huggingface/peft#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "trl"
name: "TRL"
kind: "repo"
tier: "catalog"
category: "finetune"
category_label: "Fine-tuning"
stack_layer: "model"
homepage: "http://hf.co/docs/trl"
repo: "https://github.com/huggingface/trl"
license: "Apache-2.0"
stars: 19519
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# TRL

**What:** Train models with SFT, DPO and RL.

**Why:** Teach a model your data and style.

**Category:** Fine-tuning · **Stack layer:** model

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: http://hf.co/docs/trl
- Repo: https://github.com/huggingface/trl
- README: https://github.com/huggingface/trl#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "ms-swift"
name: "ms-swift"
kind: "repo"
tier: "catalog"
category: "finetune"
category_label: "Fine-tuning"
stack_layer: "model"
homepage: "https://swift.readthedocs.io/zh-cn/latest/"
repo: "https://github.com/modelscope/ms-swift"
license: "Apache-2.0"
stars: 15860
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# ms-swift

**What:** Fine-tune 600+ LLMs with PEFT or full training.

**Why:** Teach a model your data and style.

**Category:** Fine-tuning · **Stack layer:** model

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install ms-swift -U
```

2. [any] source: README (auto-extracted); status: unverified, not executed

```bash
git clone https://github.com/modelscope/ms-swift.git
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
pip uninstall -y ms-swift
```

2. source: derived inverse of install command

```bash
rm -rf ms-swift
```

## Links

- Homepage: https://swift.readthedocs.io/zh-cn/latest/
- Repo: https://github.com/modelscope/ms-swift
- README: https://github.com/modelscope/ms-swift#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "axolotl"
name: "Axolotl"
kind: "repo"
tier: "catalog"
category: "finetune"
category_label: "Fine-tuning"
stack_layer: "model"
homepage: "https://docs.axolotl.ai"
repo: "https://github.com/axolotl-ai-cloud/axolotl"
license: "Apache-2.0"
stars: 12572
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Axolotl

**What:** Config-driven fine-tuning toolkit.

**Why:** Teach a model your data and style.

**Category:** Fine-tuning · **Stack layer:** model

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
curl -LsSf https://astral.sh/uv/install.sh | sh
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://docs.axolotl.ai
- Repo: https://github.com/axolotl-ai-cloud/axolotl
- README: https://github.com/axolotl-ai-cloud/axolotl#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "openrlhf"
name: "OpenRLHF"
kind: "repo"
tier: "catalog"
category: "finetune"
category_label: "Fine-tuning"
stack_layer: "model"
homepage: "https://openrlhf.readthedocs.io/"
repo: "https://github.com/OpenRLHF/OpenRLHF"
license: "Apache-2.0"
stars: 10089
last_push: "2026-10-05"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# OpenRLHF

**What:** Scalable RLHF and agentic RL on Ray.

**Why:** Teach a model your data and style.

**Category:** Fine-tuning · **Stack layer:** model

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install openrlhf
```

2. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install openrlhf[vllm]
```

3. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install openrlhf[vllm_latest]
```

4. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install openrlhf[vllm,ring,liger]
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
pip uninstall -y openrlhf
```

## Links

- Homepage: https://openrlhf.readthedocs.io/
- Repo: https://github.com/OpenRLHF/OpenRLHF
- README: https://github.com/OpenRLHF/OpenRLHF#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "oumi"
name: "Oumi"
kind: "repo"
tier: "catalog"
category: "finetune"
category_label: "Fine-tuning"
stack_layer: "model"
homepage: "https://oumi.ai"
repo: "https://github.com/oumi-ai/oumi"
license: "Apache-2.0"
stars: 9401
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Oumi

**What:** Fine-tune, evaluate and deploy open models.

**Why:** Teach a model your data and style.

**Category:** Fine-tuning · **Stack layer:** model

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
uv pip install oumi
```

2. [any] source: README (auto-extracted); status: unverified, not executed

```bash
docker run --gpus all -it ghcr.io/oumi-ai/oumi:latest oumi --help
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
uv pip uninstall oumi
```

## Links

- Homepage: https://oumi.ai
- Repo: https://github.com/oumi-ai/oumi
- README: https://github.com/oumi-ai/oumi#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "mergekit"
name: "MergeKit"
kind: "repo"
tier: "catalog"
category: "finetune"
category_label: "Fine-tuning"
stack_layer: "model"
homepage: null
repo: "https://github.com/arcee-ai/mergekit"
license: "LGPL-3.0"
stars: 7402
last_push: "2026-09-12"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# MergeKit

**What:** Merge model weights into new models.

**Why:** Teach a model your data and style.

**Category:** Fine-tuning · **Stack layer:** model

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
git clone https://github.com/arcee-ai/mergekit.git
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
rm -rf mergekit
```

## Links

- Repo: https://github.com/arcee-ai/mergekit
- README: https://github.com/arcee-ai/mergekit#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "thinkingbox"
name: "ThinkingBox"
kind: "repo"
tier: "catalog"
category: "evals"
category_label: "Evals & benchmarks"
stack_layer: "tools"
homepage: null
repo: "https://github.com/microsoft/thinkingbox"
license: "MIT"
stars: 102
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: ["SZsayJf_I3I"]
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-16"
---

# ThinkingBox

**What:** Runs agents against MCP tools and checks what they really did.

**Why:** Measures how close you are to the frontier.

**Category:** Evals & benchmarks · **Stack layer:** tools

## Status

Catalog entry. Existence and repo metadata checked 2026-10-16 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install -U pip setuptools
```

2. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install --config-settings editable-mode=compat -e '.[dev]'
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
pip uninstall -y pip
```

2. source: derived inverse of install command

```bash
pip uninstall -y editable-mode
```

## Links

- Repo: https://github.com/microsoft/thinkingbox
- README: https://github.com/microsoft/thinkingbox#readme
- Video: https://www.youtube.com/watch?v=SZsayJf_I3I


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "promptfoo"
name: "promptfoo"
kind: "repo"
tier: "catalog"
category: "evals"
category_label: "Evals & benchmarks"
stack_layer: "tools"
homepage: "https://promptfoo.dev"
repo: "https://github.com/promptfoo/promptfoo"
license: "MIT"
stars: 26019
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# promptfoo

**What:** Test and red-team prompts, agents and RAG.

**Why:** Measures how close you are to the frontier.

**Category:** Evals & benchmarks · **Stack layer:** tools

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
npm install -g promptfoo
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
npm uninstall -g promptfoo
```

## Links

- Homepage: https://promptfoo.dev
- Repo: https://github.com/promptfoo/promptfoo
- README: https://github.com/promptfoo/promptfoo#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "openai-evals"
name: "OpenAI Evals"
kind: "repo"
tier: "catalog"
category: "evals"
category_label: "Evals & benchmarks"
stack_layer: "tools"
homepage: null
repo: "https://github.com/openai/evals"
license: "Other"
stars: 19607
last_push: "2026-04-14"
archived: false
tags: ["slow-activity", "license-unclear"]
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# OpenAI Evals

**What:** Framework and registry for evaluating LLMs.

**Why:** Measures how close you are to the frontier.

**Category:** Evals & benchmarks · **Stack layer:** tools

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install evals
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
pip uninstall -y evals
```

## Links

- Repo: https://github.com/openai/evals
- README: https://github.com/openai/evals#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "deepeval"
name: "DeepEval"
kind: "repo"
tier: "catalog"
category: "evals"
category_label: "Evals & benchmarks"
stack_layer: "tools"
homepage: "https://deepeval.com"
repo: "https://github.com/confident-ai/deepeval"
license: "Apache-2.0"
stars: 18890
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# DeepEval

**What:** Unit-test style evaluation for LLM apps.

**Why:** Measures how close you are to the frontier.

**Category:** Evals & benchmarks · **Stack layer:** tools

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install -U deepeval
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
pip uninstall -y deepeval
```

## Links

- Homepage: https://deepeval.com
- Repo: https://github.com/confident-ai/deepeval
- README: https://github.com/confident-ai/deepeval#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "ragas"
name: "Ragas"
kind: "repo"
tier: "catalog"
category: "evals"
category_label: "Evals & benchmarks"
stack_layer: "tools"
homepage: "https://docs.ragas.io"
repo: "https://github.com/vibrantlabsai/ragas"
license: "Apache-2.0"
stars: 16034
last_push: "2026-02-24"
archived: false
tags: ["slow-activity"]
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Ragas

**What:** Metrics for evaluating RAG pipelines.

**Why:** Measures how close you are to the frontier.

**Category:** Evals & benchmarks · **Stack layer:** tools

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install ragas
```

2. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install git+https://github.com/vibrantlabsai/ragas
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
pip uninstall -y ragas
```

## Links

- Homepage: https://docs.ragas.io
- Repo: https://github.com/vibrantlabsai/ragas
- README: https://github.com/vibrantlabsai/ragas#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "lm-evaluation-harness"
name: "LM Evaluation Harness"
kind: "repo"
tier: "catalog"
category: "evals"
category_label: "Evals & benchmarks"
stack_layer: "tools"
homepage: "https://www.eleuther.ai"
repo: "https://github.com/EleutherAI/lm-evaluation-harness"
license: "MIT"
stars: 14234
last_push: "2026-09-14"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# LM Evaluation Harness

**What:** The standard harness for academic LLM benchmarks.

**Why:** Measures how close you are to the frontier.

**Category:** Evals & benchmarks · **Stack layer:** tools

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
git clone --depth 1 https://github.com/EleutherAI/lm-evaluation-harness
```

2. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install "lm_eval[hf]"
```

3. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install "lm_eval[vllm]"
```

4. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install "lm_eval[api]"
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
rm -rf https://github.com/EleutherAI/lm-evaluation-harness
```

2. source: derived inverse of install command

```bash
pip uninstall -y lm_eval
```

## Links

- Homepage: https://www.eleuther.ai
- Repo: https://github.com/EleutherAI/lm-evaluation-harness
- README: https://github.com/EleutherAI/lm-evaluation-harness#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "gorilla-bfcl"
name: "Gorilla / BFCL"
kind: "repo"
tier: "catalog"
category: "evals"
category_label: "Evals & benchmarks"
stack_layer: "tools"
homepage: "https://gorilla.cs.berkeley.edu/"
repo: "https://github.com/ShishirPatil/gorilla"
license: "Apache-2.0"
stars: 13052
last_push: "2026-04-13"
archived: false
tags: ["slow-activity"]
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Gorilla / BFCL

**What:** Function-calling models and the Berkeley tool-use leaderboard.

**Why:** Measures how close you are to the frontier.

**Category:** Evals & benchmarks · **Stack layer:** tools

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install gorilla-cli
```

2. [any] source: README (auto-extracted); status: unverified, not executed

```bash
git clone https://github.com/ShishirPatil/gorilla.git
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
pip uninstall -y gorilla-cli
```

2. source: derived inverse of install command

```bash
rm -rf gorilla
```

## Links

- Homepage: https://gorilla.cs.berkeley.edu/
- Repo: https://github.com/ShishirPatil/gorilla
- README: https://github.com/ShishirPatil/gorilla#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "opencompass"
name: "OpenCompass"
kind: "repo"
tier: "catalog"
category: "evals"
category_label: "Evals & benchmarks"
stack_layer: "tools"
homepage: "https://opencompass.org.cn/"
repo: "https://github.com/open-compass/opencompass"
license: "Apache-2.0"
stars: 7520
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# OpenCompass

**What:** Large evaluation platform across many benchmarks.

**Why:** Measures how close you are to the frontier.

**Category:** Evals & benchmarks · **Stack layer:** tools

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install -U opencompass
```

2. [any] source: README (auto-extracted); status: unverified, not executed

```bash
git clone https://github.com/open-compass/opencompass opencompass
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
pip uninstall -y opencompass
```

2. source: derived inverse of install command

```bash
rm -rf opencompass
```

## Links

- Homepage: https://opencompass.org.cn/
- Repo: https://github.com/open-compass/opencompass
- README: https://github.com/open-compass/opencompass#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "swe-bench"
name: "SWE-bench"
kind: "repo"
tier: "catalog"
category: "evals"
category_label: "Evals & benchmarks"
stack_layer: "tools"
homepage: "https://www.swebench.com"
repo: "https://github.com/SWE-bench/SWE-bench"
license: "MIT"
stars: 6033
last_push: "2026-09-18"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# SWE-bench

**What:** Benchmark of real GitHub issues for coding agents.

**Why:** Measures how close you are to the frontier.

**Category:** Evals & benchmarks · **Stack layer:** tools

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://www.swebench.com
- Repo: https://github.com/SWE-bench/SWE-bench
- README: https://github.com/SWE-bench/SWE-bench#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "simple-evals"
name: "simple-evals"
kind: "repo"
tier: "catalog"
category: "evals"
category_label: "Evals & benchmarks"
stack_layer: "tools"
homepage: null
repo: "https://github.com/openai/simple-evals"
license: "MIT"
stars: 4666
last_push: "2026-04-22"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# simple-evals

**What:** OpenAI's lightweight reference evals.

**Why:** Measures how close you are to the frontier.

**Category:** Evals & benchmarks · **Stack layer:** tools

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
git clone https://github.com/openai/human-eval
```

2. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install openai
```

3. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install anthropic
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
rm -rf human-eval
```

2. source: derived inverse of install command

```bash
pip uninstall -y openai
```

3. source: derived inverse of install command

```bash
pip uninstall -y anthropic
```

## Links

- Repo: https://github.com/openai/simple-evals
- README: https://github.com/openai/simple-evals#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "lmms-eval"
name: "LMMs-Eval"
kind: "repo"
tier: "catalog"
category: "evals"
category_label: "Evals & benchmarks"
stack_layer: "tools"
homepage: "https://www.lmms-lab.com"
repo: "https://github.com/EvolvingLMMs-Lab/lmms-eval"
license: "Other"
stars: 4453
last_push: "2026-10-15"
archived: false
tags: ["license-unclear"]
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# LMMs-Eval

**What:** Evaluation toolkit for multimodal models.

**Why:** Measures how close you are to the frontier.

**Category:** Evals & benchmarks · **Stack layer:** tools

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
git clone https://github.com/EvolvingLMMs-Lab/lmms-eval.git
```

2. [any] source: README (auto-extracted); status: unverified, not executed

```bash
uv pip install git+https://github.com/EvolvingLMMs-Lab/lmms-eval.git
```

3. [any] source: README (auto-extracted); status: unverified, not executed

```bash
conda install openjdk=8
```

4. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install s2wrapper@git+https://github.com/bfshi/scaling_on_scales
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
rm -rf lmms-eval
```

2. source: derived inverse of install command

```bash
pip uninstall -y s2wrapper@git+https://github.com/bfshi/scaling_on_scales
```

## Links

- Homepage: https://www.lmms-lab.com
- Repo: https://github.com/EvolvingLMMs-Lab/lmms-eval
- README: https://github.com/EvolvingLMMs-Lab/lmms-eval#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "inspect-ai"
name: "Inspect AI"
kind: "repo"
tier: "catalog"
category: "evals"
category_label: "Evals & benchmarks"
stack_layer: "tools"
homepage: "https://inspect.aisi.org.uk/"
repo: "https://github.com/UKGovernmentBEIS/inspect_ai"
license: "MIT"
stars: 3012
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Inspect AI

**What:** UK AISI framework for LLM and agent evals.

**Why:** Measures how close you are to the frontier.

**Category:** Evals & benchmarks · **Stack layer:** tools

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://inspect.aisi.org.uk/
- Repo: https://github.com/UKGovernmentBEIS/inspect_ai
- README: https://github.com/UKGovernmentBEIS/inspect_ai#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "terminal-bench"
name: "Terminal-Bench"
kind: "repo"
tier: "catalog"
category: "evals"
category_label: "Evals & benchmarks"
stack_layer: "tools"
homepage: "https://www.tbench.ai"
repo: "https://github.com/harbor-framework/terminal-bench-1"
license: "Apache-2.0"
stars: 2599
last_push: "2026-07-11"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Terminal-Bench

**What:** Benchmark of hard tasks in a real terminal.

**Why:** Measures how close you are to the frontier.

**Category:** Evals & benchmarks · **Stack layer:** tools

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
uv tool install terminal-bench
```

2. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install terminal-bench
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
uv tool uninstall terminal-bench
```

2. source: derived inverse of install command

```bash
pip uninstall -y terminal-bench
```

## Links

- Homepage: https://www.tbench.ai
- Repo: https://github.com/harbor-framework/terminal-bench-1
- README: https://github.com/harbor-framework/terminal-bench-1#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "lighteval"
name: "LightEval"
kind: "repo"
tier: "catalog"
category: "evals"
category_label: "Evals & benchmarks"
stack_layer: "tools"
homepage: "https://huggingface.co/docs/lighteval/en/index"
repo: "https://github.com/huggingface/lighteval"
license: "MIT"
stars: 2561
last_push: "2026-10-06"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# LightEval

**What:** Hugging Face's multi-backend eval toolkit.

**Why:** Measures how close you are to the frontier.

**Category:** Evals & benchmarks · **Stack layer:** tools

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install lighteval
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
pip uninstall -y lighteval
```

## Links

- Homepage: https://huggingface.co/docs/lighteval/en/index
- Repo: https://github.com/huggingface/lighteval
- README: https://github.com/huggingface/lighteval#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "langfuse"
name: "Langfuse"
kind: "repo"
tier: "catalog"
category: "obs"
category_label: "Observability"
stack_layer: "tools"
homepage: "https://langfuse.com"
repo: "https://github.com/langfuse/langfuse"
license: "Other"
stars: 35875
last_push: "2026-10-15"
archived: false
tags: ["license-unclear"]
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Langfuse

**What:** Open-source tracing and evals for LLM apps.

**Why:** See what your agent did and what it cost.

**Category:** Observability · **Stack layer:** tools

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://langfuse.com
- Repo: https://github.com/langfuse/langfuse
- README: https://github.com/langfuse/langfuse#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "mlflow"
name: "MLflow"
kind: "repo"
tier: "catalog"
category: "obs"
category_label: "Observability"
stack_layer: "tools"
homepage: "https://mlflow.org"
repo: "https://github.com/mlflow/mlflow"
license: "Apache-2.0"
stars: 28399
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# MLflow

**What:** ML and LLM lifecycle platform with tracing.

**Why:** See what your agent did and what it cost.

**Category:** Observability · **Stack layer:** tools

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
uvx mlflow server
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://mlflow.org
- Repo: https://github.com/mlflow/mlflow
- README: https://github.com/mlflow/mlflow#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "opik"
name: "Opik"
kind: "repo"
tier: "catalog"
category: "obs"
category_label: "Observability"
stack_layer: "tools"
homepage: "https://www.comet.com/docs/opik/"
repo: "https://github.com/comet-ml/opik"
license: "Apache-2.0"
stars: 22627
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Opik

**What:** Trace, evaluate and monitor LLM apps.

**Why:** See what your agent did and what it cost.

**Category:** Observability · **Stack layer:** tools

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install opik
```

2. [any] source: README (auto-extracted); status: unverified, not executed

```bash
uv pip install opik
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
pip uninstall -y opik
```

2. source: derived inverse of install command

```bash
uv pip uninstall opik
```

## Links

- Homepage: https://www.comet.com/docs/opik/
- Repo: https://github.com/comet-ml/opik
- README: https://github.com/comet-ml/opik#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "phoenix"
name: "Phoenix"
kind: "repo"
tier: "catalog"
category: "obs"
category_label: "Observability"
stack_layer: "tools"
homepage: "https://arize.com/docs/phoenix"
repo: "https://github.com/Arize-ai/phoenix"
license: "Other"
stars: 11858
last_push: "2026-10-15"
archived: false
tags: ["license-unclear"]
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Phoenix

**What:** Open-source LLM tracing and evaluation.

**Why:** See what your agent did and what it cost.

**Category:** Observability · **Stack layer:** tools

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install arize-phoenix
```

2. [any] source: README (auto-extracted); status: unverified, not executed

```bash
uvx arize-phoenix serve
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
pip uninstall -y arize-phoenix
```

## Links

- Homepage: https://arize.com/docs/phoenix
- Repo: https://github.com/Arize-ai/phoenix
- README: https://github.com/Arize-ai/phoenix#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "evidently"
name: "Evidently"
kind: "repo"
tier: "catalog"
category: "obs"
category_label: "Observability"
stack_layer: "tools"
homepage: "https://discord.gg/xZjKRaNp8b"
repo: "https://github.com/evidentlyai/evidently"
license: "Apache-2.0"
stars: 7991
last_push: "2026-09-29"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Evidently

**What:** Evaluate and monitor ML and LLM systems.

**Why:** See what your agent did and what it cost.

**Category:** Observability · **Stack layer:** tools

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install evidently
```

2. [any] source: README (auto-extracted); status: unverified, not executed

```bash
conda install -c conda-forge evidently
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
pip uninstall -y evidently
```

## Links

- Homepage: https://discord.gg/xZjKRaNp8b
- Repo: https://github.com/evidentlyai/evidently
- README: https://github.com/evidentlyai/evidently#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "openllmetry"
name: "OpenLLMetry"
kind: "repo"
tier: "catalog"
category: "obs"
category_label: "Observability"
stack_layer: "tools"
homepage: "https://www.traceloop.com/openllmetry"
repo: "https://github.com/traceloop/openllmetry"
license: "Apache-2.0"
stars: 7497
last_push: "2026-10-13"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# OpenLLMetry

**What:** OpenTelemetry instrumentation for LLM apps.

**Why:** See what your agent did and what it cost.

**Category:** Observability · **Stack layer:** tools

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install traceloop-sdk
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
pip uninstall -y traceloop-sdk
```

## Links

- Homepage: https://www.traceloop.com/openllmetry
- Repo: https://github.com/traceloop/openllmetry
- README: https://github.com/traceloop/openllmetry#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "helicone"
name: "Helicone"
kind: "repo"
tier: "catalog"
category: "obs"
category_label: "Observability"
stack_layer: "tools"
homepage: "https://www.helicone.ai"
repo: "https://github.com/Helicone/helicone"
license: "Apache-2.0"
stars: 6224
last_push: "2026-10-10"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Helicone

**What:** LLM observability via a one-line proxy.

**Why:** See what your agent did and what it cost.

**Category:** Observability · **Stack layer:** tools

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://www.helicone.ai
- Repo: https://github.com/Helicone/helicone
- README: https://github.com/Helicone/helicone#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "agentops"
name: "AgentOps"
kind: "repo"
tier: "catalog"
category: "obs"
category_label: "Observability"
stack_layer: "tools"
homepage: "https://agentops.ai"
repo: "https://github.com/AgentOps-AI/agentops"
license: "MIT"
stars: 5887
last_push: "2026-06-25"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# AgentOps

**What:** Monitoring and cost tracking for agents.

**Why:** See what your agent did and what it cost.

**Category:** Observability · **Stack layer:** tools

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install agentops
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
pip uninstall -y agentops
```

## Links

- Homepage: https://agentops.ai
- Repo: https://github.com/AgentOps-AI/agentops
- README: https://github.com/AgentOps-AI/agentops#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "agenta"
name: "Agenta"
kind: "repo"
tier: "catalog"
category: "obs"
category_label: "Observability"
stack_layer: "tools"
homepage: "http://www.agenta.ai"
repo: "https://github.com/Agenta-AI/agenta"
license: "Other"
stars: 4836
last_push: "2026-10-15"
archived: false
tags: ["license-unclear"]
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Agenta

**What:** Prompt management, evals and observability.

**Why:** See what your agent did and what it cost.

**Category:** Observability · **Stack layer:** tools

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. no install command found in README; follow the README or docs

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: http://www.agenta.ai
- Repo: https://github.com/Agenta-AI/agenta
- README: https://github.com/Agenta-AI/agenta#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "logfire"
name: "Logfire"
kind: "repo"
tier: "catalog"
category: "obs"
category_label: "Observability"
stack_layer: "tools"
homepage: "https://pydantic.dev/logfire/"
repo: "https://github.com/pydantic/logfire"
license: "MIT"
stars: 4512
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Logfire

**What:** Observability for LLM and agent systems.

**Why:** See what your agent did and what it cost.

**Category:** Observability · **Stack layer:** tools

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install logfire
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
pip uninstall -y logfire
```

## Links

- Homepage: https://pydantic.dev/logfire/
- Repo: https://github.com/pydantic/logfire
- README: https://github.com/pydantic/logfire#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "openlit"
name: "OpenLIT"
kind: "repo"
tier: "catalog"
category: "obs"
category_label: "Observability"
stack_layer: "tools"
homepage: "https://docs.openlit.io"
repo: "https://github.com/openlit/openlit"
license: "Apache-2.0"
stars: 2851
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# OpenLIT

**What:** OpenTelemetry-native tracing and guardrails.

**Why:** See what your agent did and what it cost.

**Category:** Observability · **Stack layer:** tools

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
git clone https://github.com/openlit/openlit.git
```

2. [any] source: README (auto-extracted); status: unverified, not executed

```bash
docker compose up -d
```

3. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install openlit
```

4. [any] source: README (auto-extracted); status: unverified, not executed

```bash
npm install openlit
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
rm -rf openlit
```

2. source: derived inverse of install command

```bash
pip uninstall -y openlit
```

## Links

- Homepage: https://docs.openlit.io
- Repo: https://github.com/openlit/openlit
- README: https://github.com/openlit/openlit#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "weave"
name: "Weave"
kind: "repo"
tier: "catalog"
category: "obs"
category_label: "Observability"
stack_layer: "tools"
homepage: "https://wandb.me/weave"
repo: "https://github.com/wandb/weave"
license: "Apache-2.0"
stars: 1141
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Weave

**What:** W&B toolkit for tracing and evaluating AI apps.

**Why:** See what your agent did and what it cost.

**Category:** Observability · **Stack layer:** tools

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
pip install weave openai-agents requests
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
pip uninstall -y weave
```

## Links

- Homepage: https://wandb.me/weave
- Repo: https://github.com/wandb/weave
- README: https://github.com/wandb/weave#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "vllm"
name: "vLLM"
kind: "repo"
tier: "catalog"
category: "runtimes"
category_label: "Runtimes & inference"
stack_layer: "runtime"
homepage: "https://vllm.ai"
repo: "https://github.com/vllm-project/vllm"
license: "Apache-2.0"
stars: 93863
last_push: "2026-10-15"
archived: false
tags: []
seen_in_videos: ["SwZtJS1OD3w"]
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# vLLM

**What:** High-throughput LLM serving engine.

**Why:** Runs open models on your own hardware.

**Category:** Runtimes & inference · **Stack layer:** runtime

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
uv pip install vllm
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
uv pip uninstall vllm
```

## Links

- Homepage: https://vllm.ai
- Repo: https://github.com/vllm-project/vllm
- README: https://github.com/vllm-project/vllm#readme
- Video: https://www.youtube.com/watch?v=SwZtJS1OD3w


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "hugging-face-hub"
name: "Hugging Face Hub"
kind: "web"
tier: "catalog"
category: "hubs"
category_label: "Model hubs"
stack_layer: "model"
homepage: "https://huggingface.co/models"
repo: null
license: null
stars: null
last_push: null
archived: null
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Hugging Face Hub

**What:** The main hub for open model weights.

**Why:** Where you find and download weights.

**Category:** Model hubs · **Stack layer:** model

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 (URL returned HTTP 200). Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: huggingface_hub CLI docs; status: documented, not executed

```bash
pip install -U huggingface_hub && hf download <org>/<model>
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://huggingface.co/models


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "ollama-library"
name: "Ollama Library"
kind: "web"
tier: "catalog"
category: "hubs"
category_label: "Model hubs"
stack_layer: "model"
homepage: "https://ollama.com/library"
repo: null
license: null
stars: null
last_push: null
archived: null
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Ollama Library

**What:** Ready-to-pull models for Ollama.

**Why:** Where you find and download weights.

**Category:** Model hubs · **Stack layer:** model

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 (URL returned HTTP 200). Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: Ollama docs; status: documented

```bash
ollama pull <model>
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: Ollama docs

```bash
ollama rm <model>
```

## Links

- Homepage: https://ollama.com/library


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "lm-studio-models"
name: "LM Studio model catalog"
kind: "web"
tier: "catalog"
category: "hubs"
category_label: "Model hubs"
stack_layer: "model"
homepage: "https://lmstudio.ai/models"
repo: null
license: null
stars: null
last_push: null
archived: null
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# LM Studio model catalog

**What:** Curated models you can load in LM Studio.

**Why:** Where you find and download weights.

**Category:** Model hubs · **Stack layer:** model

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 (URL returned HTTP 200). Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: LM Studio CLI docs; status: documented

```bash
lms get <model>
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://lmstudio.ai/models


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "mlx-community"
name: "mlx-community (Hugging Face)"
kind: "web"
tier: "catalog"
category: "hubs"
category_label: "Model hubs"
stack_layer: "model"
homepage: "https://huggingface.co/mlx-community"
repo: null
license: null
stars: null
last_push: null
archived: null
tags: ["apple-silicon"]
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# mlx-community (Hugging Face)

**What:** Community MLX conversions of popular models.

**Why:** Where you find and download weights.

**Category:** Model hubs · **Stack layer:** model

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 (URL returned HTTP 200). Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. See the homepage/README.

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://huggingface.co/mlx-community


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "unsloth-models"
name: "Unsloth (Hugging Face)"
kind: "web"
tier: "catalog"
category: "hubs"
category_label: "Model hubs"
stack_layer: "model"
homepage: "https://huggingface.co/unsloth"
repo: null
license: null
stars: null
last_push: null
archived: null
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Unsloth (Hugging Face)

**What:** Unsloth GGUF and fine-tune-ready model uploads.

**Why:** Where you find and download weights.

**Category:** Model hubs · **Stack layer:** model

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 (URL returned HTTP 200). Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. See the homepage/README.

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://huggingface.co/unsloth


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "lmstudio-community"
name: "lmstudio-community (Hugging Face)"
kind: "web"
tier: "catalog"
category: "hubs"
category_label: "Model hubs"
stack_layer: "model"
homepage: "https://huggingface.co/lmstudio-community"
repo: null
license: null
stars: null
last_push: null
archived: null
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# lmstudio-community (Hugging Face)

**What:** LM Studio's community GGUF/MLX uploads.

**Why:** Where you find and download weights.

**Category:** Model hubs · **Stack layer:** model

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 (URL returned HTTP 200). Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. See the homepage/README.

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://huggingface.co/lmstudio-community


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "kaggle-models"
name: "Kaggle Models"
kind: "web"
tier: "catalog"
category: "hubs"
category_label: "Model hubs"
stack_layer: "model"
homepage: "https://www.kaggle.com/models"
repo: null
license: null
stars: null
last_push: null
archived: null
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Kaggle Models

**What:** Google-run model hub with downloadable weights.

**Why:** Where you find and download weights.

**Category:** Model hubs · **Stack layer:** model

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 (URL returned HTTP 200). Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. See the homepage/README.

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://www.kaggle.com/models


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "lm-studio-bionic"
name: "LM Studio Bionic"
kind: "web"
tier: "catalog"
category: "general"
category_label: "General & personal agents"
stack_layer: "harness"
homepage: "https://lmstudio.ai/bionic"
repo: null
license: null
stars: null
last_push: null
archived: null
tags: ["closed-source", "apple-silicon"]
seen_in_videos: ["SE_nPi7eeyI"]
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-16"
---

# LM Studio Bionic

**What:** LM Studio's agent that can run beside the app.

**Why:** Lets a model take actions for you, not just chat.

**Category:** General & personal agents · **Stack layer:** harness

## Status

Catalog entry. Existence and repo metadata checked 2026-10-16 (URL returned HTTP 200). Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. See the homepage/README.

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://lmstudio.ai/bionic
- Video: https://www.youtube.com/watch?v=SE_nPi7eeyI


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "soul-md"
name: "SOUL.md (persona file)"
kind: "web"
tier: "catalog"
category: "scaffolds"
category_label: "Scaffolds & templates"
stack_layer: "harness"
homepage: "https://hermes-agent.nousresearch.com/docs/user-guide/features/personality"
repo: null
license: null
stars: null
last_push: null
archived: null
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# SOUL.md (persona file)

**What:** A file that sets your agent's identity and voice.

**Why:** Reusable instructions that make agents behave.

**Category:** Scaffolds & templates · **Stack layer:** harness

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 (URL returned HTTP 200). Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

No install command found. See the homepage/README.

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

No derived rollback. Remove what the install created (see README).

## Links

- Homepage: https://hermes-agent.nousresearch.com/docs/user-guide/features/personality
- Docs: https://hermes-agent.nousresearch.com/docs/user-guide/features/personality
- Docs: https://docs.openclaw.ai/concepts/soul


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "qwen-image-2-1-turbo"
name: "Qwen-Image-2.1-Turbo"
kind: "model"
tier: "catalog"
category: "models"
category_label: "Models from the channel"
stack_layer: "model"
homepage: "https://huggingface.co/Qwen/Qwen-Image-2.1-Turbo"
repo: null
license: "Qwen Research License (non-commercial)"
stars: null
last_push: null
archived: null
tags: []
seen_in_videos: ["SE_nPi7eeyI"]
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-16"
---

# Qwen-Image-2.1-Turbo

**What:** 7B image model that paints and edits in 8 steps.

**Why:** Featured on Inside the Machine; check the fit before you download.

**Category:** Models from the channel · **Stack layer:** model

## Status

Catalog entry. Existence and repo metadata checked 2026-10-16 via the Hugging Face API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: huggingface_hub CLI docs (generic); status: documented, not executed

```bash
hf download Qwen/Qwen-Image-2.1-Turbo
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: huggingface_hub cache docs

```bash
hf cache rm Qwen/Qwen-Image-2.1-Turbo  # or delete it from ~/.cache/huggingface/hub
```

## Links

- Homepage: https://huggingface.co/Qwen/Qwen-Image-2.1-Turbo
- Video: https://www.youtube.com/watch?v=SE_nPi7eeyI


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "mellum-2-1"
name: "Mellum2.1 12B-A2.5B"
kind: "model"
tier: "catalog"
category: "models"
category_label: "Models from the channel"
stack_layer: "model"
homepage: "https://huggingface.co/JetBrains/Mellum2.1-12B-A2.5B-Thinking"
repo: null
license: "apache-2.0"
stars: null
last_push: null
archived: null
tags: []
seen_in_videos: ["_JhhrV3VDqg"]
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Mellum2.1 12B-A2.5B

**What:** JetBrains coding model, 12B with 2.5B active.

**Why:** Featured on Inside the Machine; check the fit before you download.

**Category:** Models from the channel · **Stack layer:** model

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the Hugging Face API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: huggingface_hub CLI docs (generic); status: documented, not executed

```bash
hf download JetBrains/Mellum2.1-12B-A2.5B-Thinking
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: huggingface_hub cache docs

```bash
hf cache rm JetBrains/Mellum2.1-12B-A2.5B-Thinking  # or delete it from ~/.cache/huggingface/hub
```

## Links

- Homepage: https://huggingface.co/JetBrains/Mellum2.1-12B-A2.5B-Thinking
- Video: https://www.youtube.com/watch?v=_JhhrV3VDqg


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "embeddinggemma-2"
name: "EmbeddingGemma 2"
kind: "model"
tier: "catalog"
category: "models"
category_label: "Models from the channel"
stack_layer: "model"
homepage: "https://huggingface.co/google/embeddinggemma-2"
repo: null
license: "apache-2.0"
stars: null
last_push: null
archived: null
tags: []
seen_in_videos: ["SwZtJS1OD3w"]
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-16"
---

# EmbeddingGemma 2

**What:** 740M on-device embedding model for search.

**Why:** Featured on Inside the Machine; check the fit before you download.

**Category:** Models from the channel · **Stack layer:** model

## Status

Catalog entry. Existence and repo metadata checked 2026-10-16 via the Hugging Face API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: ollama.com/library/embeddinggemma-2 (HTTP 200); status: documented, not executed

```bash
ollama pull embeddinggemma-2
```

2. [any] source: huggingface_hub CLI docs (generic); status: documented, not executed

```bash
hf download google/embeddinggemma-2
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: huggingface_hub cache docs

```bash
hf cache rm google/embeddinggemma-2  # or delete it from ~/.cache/huggingface/hub
```

## Links

- Homepage: https://huggingface.co/google/embeddinggemma-2
- Video: https://www.youtube.com/watch?v=SwZtJS1OD3w


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "kolibri-1"
name: "Kolibri-1"
kind: "model"
tier: "catalog"
category: "models"
category_label: "Models from the channel"
stack_layer: "model"
homepage: "https://huggingface.co/Aleph-Alpha/Kolibri-1"
repo: null
license: "apache-2.0"
stars: null
last_push: null
archived: null
tags: []
seen_in_videos: ["SZsayJf_I3I"]
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# Kolibri-1

**What:** Open German/English MoE model (about 78 GB of memory, per the video).

**Why:** Featured on Inside the Machine; check the fit before you download.

**Category:** Models from the channel · **Stack layer:** model

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the Hugging Face API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: huggingface_hub CLI docs (generic); status: documented, not executed

```bash
hf download Aleph-Alpha/Kolibri-1
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: huggingface_hub cache docs

```bash
hf cache rm Aleph-Alpha/Kolibri-1  # or delete it from ~/.cache/huggingface/hub
```

## Links

- Homepage: https://huggingface.co/Aleph-Alpha/Kolibri-1
- Video: https://www.youtube.com/watch?v=SZsayJf_I3I


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "astabrief-8b"
name: "AstaBrief 8B"
kind: "model"
tier: "catalog"
category: "models"
category_label: "Models from the channel"
stack_layer: "model"
homepage: "https://huggingface.co/allenai/AstaBrief_8B"
repo: null
license: "apache-2.0"
stars: null
last_push: null
archived: null
tags: []
seen_in_videos: ["SZsayJf_I3I"]
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-15"
---

# AstaBrief 8B

**What:** Small Ai2 model that writes cited reports.

**Why:** Featured on Inside the Machine; check the fit before you download.

**Category:** Models from the channel · **Stack layer:** model

## Status

Catalog entry. Existence and repo metadata checked 2026-10-15 via the Hugging Face API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: huggingface_hub CLI docs (generic); status: documented, not executed

```bash
hf download allenai/AstaBrief_8B
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: huggingface_hub cache docs

```bash
hf cache rm allenai/AstaBrief_8B  # or delete it from ~/.cache/huggingface/hub
```

## Links

- Homepage: https://huggingface.co/allenai/AstaBrief_8B
- Video: https://www.youtube.com/watch?v=SZsayJf_I3I


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "cloudflare-clef"
name: "Clef"
kind: "model"
tier: "catalog"
category: "models"
category_label: "Models from the channel"
stack_layer: "model"
homepage: "https://huggingface.co/Cloudflare/clef"
repo: null
license: "apache-2.0"
stars: null
last_push: null
archived: null
tags: []
seen_in_videos: ["q9QJlZBgOGE"]
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-16"
---

# Clef

**What:** Cloudflare's small open decision models (Clef, Clef-flash).

**Why:** Featured on Inside the Machine; check the fit before you download.

**Category:** Models from the channel · **Stack layer:** model

## Status

Catalog entry. Existence and repo metadata checked 2026-10-16 via the Hugging Face API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: huggingface_hub CLI docs (generic); status: documented, not executed

```bash
hf download Cloudflare/clef
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: huggingface_hub cache docs

```bash
hf cache rm Cloudflare/clef  # or delete it from ~/.cache/huggingface/hub
```

## Links

- Homepage: https://huggingface.co/Cloudflare/clef
- Video: https://www.youtube.com/watch?v=q9QJlZBgOGE


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "copilot-cli"
name: "GitHub Copilot CLI"
kind: "repo"
tier: "catalog"
category: "coding"
category_label: "Coding agents"
stack_layer: "harness"
homepage: "https://github.com/features/copilot/cli"
repo: "https://github.com/github/copilot-cli"
license: null
stars: 11262
last_push: "2026-10-16"
archived: false
tags: ["cloud-model", "license-unclear"]
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-16"
---

# GitHub Copilot CLI

**What:** GitHub's terminal coding agent; can use Ollama models.

**Why:** Turns a model into something that edits your code.

**Category:** Coding agents · **Stack layer:** harness

> Note: Needs a Copilot subscription. Uses GitHub's cloud models unless you pick a local one.

## Status

Catalog entry. Existence and repo metadata checked 2026-10-16 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [any] source: README (auto-extracted); status: unverified, not executed

```bash
curl -fsSL https://gh.io/copilot-install | bash
```

2. [macos] source: README (auto-extracted); status: unverified, not executed

```bash
brew install copilot-cli
```

3. [windows] source: README (auto-extracted); status: unverified, not executed

```bash
winget install GitHub.Copilot
```

4. [any] source: README (auto-extracted); status: unverified, not executed

```bash
npm install -g @github/copilot
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
brew uninstall copilot-cli
```

2. source: derived inverse of install command

```bash
winget uninstall GitHub.Copilot
```

3. source: derived inverse of install command

```bash
npm uninstall -g @github/copilot
```

## Links

- Homepage: https://github.com/features/copilot/cli
- Repo: https://github.com/github/copilot-cli
- README: https://github.com/github/copilot-cli#readme


---

---
schema: "https://insidethemachine.ai/schema/listing.schema.json"
slug: "nvidia-pair"
name: "NVIDIA PAIR"
kind: "repo"
tier: "catalog"
category: "routing"
category_label: "Routing & gateways"
stack_layer: "runtime"
homepage: null
repo: "https://github.com/NVIDIA/Personal-AI-Router"
license: "Apache-2.0"
stars: 1621
last_push: "2026-10-14"
archived: false
tags: []
seen_in_videos: []
gap_score: null
gap_score_status: "pending test on Mac Studio"
verified_on: "2026-10-16"
---

# NVIDIA PAIR

**What:** Shares AI requests across the computers on your home network.

**Why:** Sends each request to the right model.

**Category:** Routing & gateways · **Stack layer:** runtime

## Status

Catalog entry. Existence and repo metadata checked 2026-10-16 via the GitHub API. Install commands below are auto-extracted from the README and have NOT been executed or verified. Read the README before running anything; prefer a sandbox or venv.

## Install (unverified)

1. [linux] source: README (auto-extracted); status: unverified, not executed

```bash
sudo apt install ./NVPAIR-Setup-*.deb
```

## Verify

No verified check yet. Minimum: the install command exits 0 and the tool's own help/version flag runs (exact flag: see README).

## Rollback (unverified)

1. source: derived inverse of install command

```bash
sudo apt remove nvpair
```

## Links

- Repo: https://github.com/NVIDIA/Personal-AI-Router
- README: https://github.com/NVIDIA/Personal-AI-Router#readme


---

# Pages

# Recipes: what do you want to do?

URL: https://insidethemachine.ai/do
6 step-by-step recipes for running AI on your own computer. Mac first. Each recipe page has the tools, the model for each memory size, exact commands, expected output, rollback, fixes and Windows notes.
New to local AI? Read https://insidethemachine.ai/start-here.md first.

| id | goal | what | needs GB | best GB | minutes | tools | markdown | json |
|---|---|---|---|---|---|---|---|---|
| chat | A private ChatGPT | Chat, write and brainstorm. Nothing leaves your computer. | 8 | 16 | 10 | ollama, open-webui | https://insidethemachine.ai/do/chat.md | https://insidethemachine.ai/do/chat.json |
| code | A coding helper | An assistant that reads and edits your code. | 16 | 32 | 15 | ollama, opencode, aider | https://insidethemachine.ai/do/code.md | https://insidethemachine.ai/do/code.json |
| docs | Chat with your files | Ask questions about your PDFs, notes and documents. | 16 | 32 | 20 | ollama, open-webui, docling | https://insidethemachine.ai/do/docs.md | https://insidethemachine.ai/do/docs.json |
| voice | Speech to text | Turn meetings and voice notes into text, offline. | 8 | 16 | 10 | whisper-cpp, handy | https://insidethemachine.ai/do/voice.md | https://insidethemachine.ai/do/voice.json |
| images | Make images | Create pictures from a text prompt on your own machine. | 16 | 32 | 20 | draw-things, comfyui | https://insidethemachine.ai/do/images.md | https://insidethemachine.ai/do/images.json |
| agent | An agent that does tasks | It remembers you, uses tools and learns new skills. | 32 | 64 | 30 | hermes-agent, mcp-servers | https://insidethemachine.ai/do/agent.md | https://insidethemachine.ai/do/agent.json |

Pick: the highest-memory goal the machine meets (needs GB = total RAM, or VRAM on a PC with a graphics card). Model per memory size: https://insidethemachine.ai/models.md. App per job: https://insidethemachine.ai/harnesses.md.


---

# Recipe: A private ChatGPT

A ChatGPT-style chat app that runs fully on your computer, even offline.

URL: https://insidethemachine.ai/do/chat
Memory: needs 8 GB+, best with 16 GB+. Platform: macOS (Apple silicon) first.
Run end to end on an Apple M4 Mac with 16 GB on 2026-10-15.

## Model by memory (replace {MODEL})

| RAM GB | model | ollama tag | needs GB |
|---|---|---|---|
| 8 | Qwen3.5 4B | qwen3.5:4b | 5.8 |
| 16 | Gemma 4 12B | gemma4:12b | 11.2 |
| 24 | Gemma 4 12B | gemma4:12b | 11.2 |
| 32 | Qwen3.8 27B | qwen3.8:27b | 22.7 |
| 48 | Qwen3.8 27B | qwen3.8:27b | 22.7 |
| 64 | Qwen3.8 27B | qwen3.8:27b | 22.7 |
| 96 | Qwen3.8 27B | qwen3.8:27b | 22.7 |
| 128 | Qwen3.8 27B | qwen3.8:27b | 22.7 |
| 192 | Qwen3.8-Flash-Next (125B-A6B) | qwen3.8-flash-next:125b-a6b | 140 |
| 256 | Qwen3.8-Flash-Next (125B-A6B) | qwen3.8-flash-next:125b-a6b | 140 |
| 512 | Qwen3.8-Flash-Next (125B-A6B) | qwen3.8-flash-next:125b-a6b | 140 |

## Steps

1. **Install Ollama**: Ollama downloads AI models and runs them on your computer. Open the Terminal app and paste this. It may ask for your Mac password.
   ```sh
   curl -fsSL https://ollama.com/install.sh | sh
   ```
   (Or download the app from ollama.com/download)
   Expect: Run `ollama --version`. It prints a version number. If it also says “could not connect”, open Ollama from your Applications folder, wait a few seconds, then go on.
2. **Download your model**: This is the AI itself. It is one big file, so it takes a few minutes.
   ```sh
   ollama pull {MODEL}
   ```
   Expect: The download finishes with “success”.
3. **Say hi**: Chat right in the Terminal to check it works.
   ```sh
   ollama run {MODEL}
   ```
   (Type a message. Type /bye to quit.)
   Expect: The model answers you. That answer came from your own computer.
4. **Add a ChatGPT-style window**: Open WebUI gives you a chat app in your browser. It needs Homebrew (brew.sh) for Python.
   ```sh
   brew install python@3.11
   ```
   ```sh
   python3.11 -m venv ~/.venvs/openwebui && source ~/.venvs/openwebui/bin/activate
   ```
   ```sh
   pip install open-webui
   ```
   ```sh
   open-webui serve
   ```
   (Keep this window open while you use it)
   Expect: Open http://localhost:8080. Make a local account (it stays on your computer) and pick your model at the top.

## Alternative

Prefer no Terminal? Use LM Studio. Download the app from lmstudio.ai, search for your model by name, click Download, then chat. Everything is point and click. (https://insidethemachine.ai/setups/lm-studio)

## Rollback

- `ollama rm {MODEL}` (Removes the model file)
- `rm -rf ~/.venvs/openwebui` (Removes Open WebUI)
- `rm -rf ~/Library/Caches/pip` (Removes about 1.5 GB of saved downloads)

## One-command install

```bash
curl -fsSL https://insidethemachine.ai/install/chat.sh | bash             # install, then check
curl -fsSL https://insidethemachine.ai/install/chat.sh | bash -s -- plan     # print only
curl -fsSL https://insidethemachine.ai/install/chat.sh | bash -s -- rollback --yes
```

Run status and Windows: https://insidethemachine.ai/install/chat.md. The script picks {MODEL} from the machine's memory (override: ITM_RAM, ITM_MODEL).

## Notes

- Check your free disk space first. You need room for the model (a bit less than the memory it needs) plus about 4 GB for Open WebUI.
- The first answer is slow while the model loads. On a 16 GB Mac it took about 1.5 minutes. After that it is quick.
- Open WebUI uses port 8080. Other local AI servers sometimes use it too.

## If something goes wrong

- “could not connect to ollama app, is it running?”: Ollama is not running. Open Ollama from your Applications folder, or run `ollama serve` in a new Terminal window and leave it open.
- “command not found: ollama”: Close the Terminal window and open a new one. If it still fails, run the install command again.
- “model requires more system memory”: The model is too big for your memory. Pick a smaller memory size at the top of this page and use that model. Close other big apps too.
- “file does not exist” when you download: The model name is wrong, or Ollama is too old. Copy the command again from this page. Then update Ollama: run the install command again.
- It is very slow: Run `ollama ps`. PROCESSOR should say 100% GPU. If it shows CPU, the model does not fit in memory. Pick a smaller model.
- The computer freezes, or the fan is loud: The model uses all your memory. Stop it with `ollama stop {MODEL}`. Then use a smaller one.
- “address already in use” when Open WebUI starts: Another app uses port 8080. Run `open-webui serve --port 8081`, then open http://localhost:8081.
- No models in the list at the top of Open WebUI: Ollama is not running. Start it, then reload the page.

## After it works

- Try it: paste a long email and ask “sum this up in 3 lines”. Ask it to rewrite a text so it sounds friendlier. Ask it to explain a hard idea step by step.
- See every model you have: `ollama list`.
- Try a different model: copy any `ollama run` name from the Models page.
- Update your model: run `ollama pull {MODEL}` again. It only downloads what changed.
- Free disk space: `ollama rm {MODEL}` deletes a model you no longer use.

## Windows / Linux (not tested by us)

Install Ollama with this PowerShell command, or the installer from ollama.com/download. On Linux, the install command above works as it is. After that, every `ollama` command on this page is the same. For the chat window on Windows, LM Studio (lmstudio.ai) is the easiest. Open WebUI also runs on Windows; see its page.

```powershell
irm https://ollama.com/install.ps1 | iex
```
(Windows: paste in PowerShell. Or get the installer from ollama.com/download)


---

# Recipe: A coding helper

An AI coding agent in your Terminal that reads your project, edits files and runs commands, with changes you can undo.

URL: https://insidethemachine.ai/do/code
Memory: needs 16 GB+, best with 32 GB+. Platform: macOS (Apple silicon) first.
The under-32 GB path (Aider) was run end to end on an Apple M4 Mac with 16 GB on 2026-10-15. The OpenCode path is checked against the docs only.

## Model by memory (replace {MODEL})

| RAM GB | model | ollama tag | needs GB |
|---|---|---|---|
| 8 | Qwen3.5 4B | qwen3.5:4b | 5.8 |
| 16 | Ornith 1.5 9B | ornith-1.5:9b | 8.8 |
| 24 | Gemma 4 12B | gemma4:12b | 11.2 |
| 32 | Qwen3.8 27B | qwen3.8:27b | 22.7 |
| 48 | Qwen3.8 27B | qwen3.8:27b | 22.7 |
| 64 | Qwen3.8 27B | qwen3.8:27b | 22.7 |
| 96 | Qwen3.8 27B | qwen3.8:27b | 22.7 |
| 128 | Qwen3.8 27B | qwen3.8:27b | 22.7 |
| 192 | Qwen3.8-Flash-Next (125B-A6B) | qwen3.8-flash-next:125b-a6b | 140 |
| 256 | Qwen3.8-Flash-Next (125B-A6B) | qwen3.8-flash-next:125b-a6b | 140 |
| 512 | Qwen3.8-Flash-Next (125B-A6B) | qwen3.8-flash-next:125b-a6b | 140 |

## Steps

1. **Install Ollama**: Ollama downloads AI models and runs them on your computer. Open the Terminal app and paste this. It may ask for your Mac password.
   ```sh
   curl -fsSL https://ollama.com/install.sh | sh
   ```
   (Or download the app from ollama.com/download)
   Expect: Run `ollama --version`. It prints a version number. If it also says “could not connect”, open Ollama from your Applications folder, wait a few seconds, then go on.
2. **Download a coding model**: This is the AI itself. It is one big file, so it takes a few minutes.
   ```sh
   ollama pull {MODEL}
   ```
   Expect: The download finishes with “success”.
3. **Give the model a long memory**: OpenCode needs at least 64k of context (how much text the model reads at once). Quit the Ollama menu-bar app, then start Ollama like this. Leave this window open.
   ```sh
   OLLAMA_CONTEXT_LENGTH=64000 ollama serve
   ```
4. **Install OpenCode**: OpenCode is the coding agent. Open a second Terminal window.
   ```sh
   curl -fsSL https://opencode.ai/install | bash
   ```
   (Or with Homebrew: brew install anomalyco/tap/opencode)
   Expect: Run `opencode --version`. It prints a version.
5. **Start it in your project**: Go to your project folder, then let Ollama start OpenCode. When it asks for a model, pick {MODEL}.
   ```sh
   cd /path/to/your/project
   ```
   ```sh
   ollama launch opencode
   ```
   Expect: Ask “explain this project”. It answers about your files.

## Alternative

Prefer a simpler helper? Use Aider. Aider edits files and commits each change to git. It works with smaller models that cannot use tools. It has had no new release since August 2025. (https://insidethemachine.ai/setups/aider)

## Rollback

- `rm -rf ~/.opencode` (Removes OpenCode from the install script. Also delete the line with .opencode/bin in ~/.zshrc. With Homebrew: brew uninstall opencode)
- `ollama rm {MODEL}`

## One-command install

```bash
curl -fsSL https://insidethemachine.ai/install/code.sh | bash             # install, then check
curl -fsSL https://insidethemachine.ai/install/code.sh | bash -s -- plan     # print only
curl -fsSL https://insidethemachine.ai/install/code.sh | bash -s -- rollback --yes
```

Run status and Windows: https://insidethemachine.ai/install/code.md. The script picks {MODEL} from the machine's memory (override: ITM_RAM, ITM_MODEL).

## Notes

- Check your free disk space first. You need room for the model plus about 1 GB for OpenCode.
- Local models handle small, clear tasks best. Ask for one change at a time.
- Type `/undo` in OpenCode to take back its last change. `/redo` brings it back.
- If it is slow, run `ollama ps`. PROCESSOR should say 100% GPU. If not, the model and its 64k memory do not fit.

## If something goes wrong

- “could not connect to ollama app, is it running?”: Ollama is not running. Open Ollama from your Applications folder, or run `ollama serve` in a new Terminal window and leave it open.
- “command not found: ollama”: Close the Terminal window and open a new one. If it still fails, run the install command again.
- “model requires more system memory”: The model is too big for your memory. Pick a smaller memory size at the top of this page and use that model. Close other big apps too.
- “file does not exist” when you download: The model name is wrong, or Ollama is too old. Copy the command again from this page. Then update Ollama: run the install command again.
- It is very slow: Run `ollama ps`. PROCESSOR should say 100% GPU. If it shows CPU, the model does not fit in memory. Pick a smaller model.
- The computer freezes, or the fan is loud: The model uses all your memory. Stop it with `ollama stop {MODEL}`. Then use a smaller one.
- It talks, but it does not change any files: The model is too small to use tools. Use a bigger model, or Aider (the box above), which does not need tools.
- It forgets the start of the job: Ollama was started without the long memory. Quit Ollama and run step 3 again.

## After it works

- Try it: ask “explain this project”, then “add a comment to the main function”. Small, clear jobs work best.
- Before a big change, commit your work in git. Then you can always go back.
- See every model you have: `ollama list`.
- Try a different model: copy any `ollama run` name from the Models page.
- Update your model: run `ollama pull {MODEL}` again. It only downloads what changed.
- Free disk space: `ollama rm {MODEL}` deletes a model you no longer use.

## Windows / Linux (not tested by us)

Install Ollama with this PowerShell command, or the installer from ollama.com/download. On Linux, the install command above works as it is. After that, every `ollama` command on this page is the same. In PowerShell, start Ollama with a long memory like this. OpenCode runs on Windows too; see opencode.ai/docs. Aider's page has its Windows steps.

```powershell
irm https://ollama.com/install.ps1 | iex
```
(Windows: paste in PowerShell. Or get the installer from ollama.com/download)
```powershell
$env:OLLAMA_CONTEXT_LENGTH=64000; ollama serve
```
(PowerShell version of step 3)

## If the computer has under 32 GB

Under 32 GB, the models that fit cannot use tools well, and OpenCode needs tools. So this path uses Aider, which does not need them. Use these steps instead.

1. **Install Ollama**: Ollama downloads AI models and runs them on your computer. Open the Terminal app and paste this. It may ask for your Mac password.
   ```sh
   curl -fsSL https://ollama.com/install.sh | sh
   ```
   (Or download the app from ollama.com/download)
   Expect: Run `ollama --version`. It prints a version number. If it also says “could not connect”, open Ollama from your Applications folder, wait a few seconds, then go on.
2. **Download a coding model**: This is the AI itself. It is one big file, so it takes a few minutes.
   ```sh
   ollama pull {MODEL}
   ```
   Expect: The download finishes with “success”.
3. **Give the model more room**: Code needs a longer memory than chat. Quit the Ollama menu-bar app, then start Ollama like this. Leave this window open.
   ```sh
   OLLAMA_CONTEXT_LENGTH=8192 ollama serve
   ```
4. **Install Aider**: Aider is the coding helper. Open a second Terminal window. It installs with uv, a Python tool manager. Skip the first line if you already have uv.
   ```sh
   brew install uv
   ```
   (Needs Homebrew (brew.sh))
   ```sh
   uv tool install --force --python python3.12 --with pip aider-chat@latest
   ```
   Expect: Run `aider --version`. It prints a version.
5. **Start it in your project**: Go to a project folder that uses git, then start Aider with your model.
   ```sh
   export OLLAMA_API_BASE=http://127.0.0.1:11434
   ```
   ```sh
   cd /path/to/your/project
   ```
   ```sh
   aider --model ollama_chat/{MODEL}
   ```
   Expect: Ask “explain this project”. It answers about your files.

Rollback: `uv tool uninstall aider-chat`, `ollama rm {MODEL}`

Notes: Check your free disk space first. You need room for the model plus about 1 GB for Aider. Local models handle small, clear tasks best. Ask for one change at a time. On a 16 GB Mac an answer took about 1 minute. Aider commits each change to git, so `/undo` takes it back. Aider has had no new release since August 2025. It still works with Ollama.

Windows on this path: Install Ollama with this PowerShell command, or the installer from ollama.com/download. On Linux, the install command above works as it is. After that, every `ollama` command on this page is the same. In PowerShell, start Ollama with more room like this. Aider's page has its Windows steps. `irm https://ollama.com/install.ps1 | iex`, `$env:OLLAMA_CONTEXT_LENGTH=8192; ollama serve`

If something goes wrong on this path: “could not connect to ollama app, is it running?”: Ollama is not running. Open Ollama from your Applications folder, or run `ollama serve` in a new Terminal window and leave it open. “command not found: ollama”: Close the Terminal window and open a new one. If it still fails, run the install command again. “model requires more system memory”: The model is too big for your memory. Pick a smaller memory size at the top of this page and use that model. Close other big apps too. “file does not exist” when you download: The model name is wrong, or Ollama is too old. Copy the command again from this page. Then update Ollama: run the install command again. It is very slow: Run `ollama ps`. PROCESSOR should say 100% GPU. If it shows CPU, the model does not fit in memory. Pick a smaller model. The computer freezes, or the fan is loud: The model uses all your memory. Stop it with `ollama stop {MODEL}`. Then use a smaller one. A warning about “unknown context window size”: You can ignore it. Aider still works with your model. “aider: command not found”: Close the Terminal window and open a new one. If it still fails, run `uv tool update-shell` and open a new window.


---

# Recipe: Chat with your files

A private chat that answers questions about your own PDFs, notes and documents.

URL: https://insidethemachine.ai/do/docs
Memory: needs 16 GB+, best with 32 GB+. Platform: macOS (Apple silicon) first.
Install steps run on an Apple M4 Mac with 16 GB on 2026-10-15. File upload and the first Docling run are checked against the docs only.

## Model by memory (replace {MODEL})

| RAM GB | model | ollama tag | needs GB |
|---|---|---|---|
| 8 | Qwen3.5 4B | qwen3.5:4b | 5.8 |
| 16 | Gemma 4 12B | gemma4:12b | 11.2 |
| 24 | Gemma 4 12B | gemma4:12b | 11.2 |
| 32 | Qwen3.8 27B | qwen3.8:27b | 22.7 |
| 48 | Qwen3.8 27B | qwen3.8:27b | 22.7 |
| 64 | Qwen3.8 27B | qwen3.8:27b | 22.7 |
| 96 | Qwen3.8 27B | qwen3.8:27b | 22.7 |
| 128 | Qwen3.8 27B | qwen3.8:27b | 22.7 |
| 192 | Qwen3.8-Flash-Next (125B-A6B) | qwen3.8-flash-next:125b-a6b | 140 |
| 256 | Qwen3.8-Flash-Next (125B-A6B) | qwen3.8-flash-next:125b-a6b | 140 |
| 512 | Qwen3.8-Flash-Next (125B-A6B) | qwen3.8-flash-next:125b-a6b | 140 |

## Steps

1. **Install Ollama**: Ollama downloads AI models and runs them on your computer. Open the Terminal app and paste this. It may ask for your Mac password.
   ```sh
   curl -fsSL https://ollama.com/install.sh | sh
   ```
   (Or download the app from ollama.com/download)
   Expect: Run `ollama --version`. It prints a version number. If it also says “could not connect”, open Ollama from your Applications folder, wait a few seconds, then go on.
2. **Download your model**: This is the AI itself. It is one big file, so it takes a few minutes.
   ```sh
   ollama pull {MODEL}
   ```
   Expect: The download finishes with “success”.
3. **Add a ChatGPT-style window**: Open WebUI gives you a chat app in your browser. It needs Homebrew (brew.sh) for Python.
   ```sh
   brew install python@3.11
   ```
   ```sh
   python3.11 -m venv ~/.venvs/openwebui && source ~/.venvs/openwebui/bin/activate
   ```
   ```sh
   pip install open-webui
   ```
   ```sh
   open-webui serve
   ```
   (Keep this window open while you use it)
   Expect: Open http://localhost:8080. Make a local account (it stays on your computer) and pick your model at the top.
4. **Add your files**: In a chat, click + and attach a file, then ask about it. For a whole folder, go to Workspace → Knowledge, make a collection and upload your files. Then type # in a chat to use it.

   Expect: The answer quotes your document.
5. **Messy PDF? Clean it first**: Scanned or complex PDFs give bad answers. Docling turns them into clean text you can upload instead.
   ```sh
   python3 -m venv ~/.venvs/docling && source ~/.venvs/docling/bin/activate
   ```
   ```sh
   pip install docling
   ```
   ```sh
   docling yourfile.pdf
   ```
   (Writes yourfile.md next to it)
   Expect: A Markdown file appears. Upload that one.

## Alternative

Prefer one app? Use AnythingLLM. AnythingLLM is a desktop app for chatting with your documents. Download it from anythingllm.com and choose Ollama as the model provider. (https://insidethemachine.ai/setups/anythingllm)

## Rollback

- `ollama rm {MODEL}` (Removes the model file)
- `rm -rf ~/.venvs/openwebui ~/.venvs/docling` (Removes Open WebUI and Docling)
- `rm -rf ~/Library/Caches/pip` (Removes saved downloads)

## One-command install

```bash
curl -fsSL https://insidethemachine.ai/install/docs.sh | bash             # install, then check
curl -fsSL https://insidethemachine.ai/install/docs.sh | bash -s -- plan     # print only
curl -fsSL https://insidethemachine.ai/install/docs.sh | bash -s -- rollback --yes
```

Run status and Windows: https://insidethemachine.ai/install/docs.md. The script picks {MODEL} from the machine's memory (override: ITM_RAM, ITM_MODEL).

## Notes

- Check your free disk space first. You need room for the model plus about 4 GB for Open WebUI and 2 GB for Docling.
- The first Docling run downloads its own small models.
- Answers are only as good as the text it can read. Clean files give better answers.

## If something goes wrong

- “could not connect to ollama app, is it running?”: Ollama is not running. Open Ollama from your Applications folder, or run `ollama serve` in a new Terminal window and leave it open.
- “command not found: ollama”: Close the Terminal window and open a new one. If it still fails, run the install command again.
- “model requires more system memory”: The model is too big for your memory. Pick a smaller memory size at the top of this page and use that model. Close other big apps too.
- “file does not exist” when you download: The model name is wrong, or Ollama is too old. Copy the command again from this page. Then update Ollama: run the install command again.
- It is very slow: Run `ollama ps`. PROCESSOR should say 100% GPU. If it shows CPU, the model does not fit in memory. Pick a smaller model.
- The computer freezes, or the fan is loud: The model uses all your memory. Stop it with `ollama stop {MODEL}`. Then use a smaller one.
- “address already in use” when Open WebUI starts: Another app uses port 8080. Run `open-webui serve --port 8081`, then open http://localhost:8081.
- No models in the list at the top of Open WebUI: Ollama is not running. Start it, then reload the page.
- The answer ignores your file: Check that the file shows in the chat. Scanned PDFs have no real text; clean them with Docling (step 5) and upload the .md file.

## After it works

- Try it: upload a manual and ask “how do I reset it?”. Upload notes and ask “what did we decide?”.
- Make a Knowledge collection per topic, so answers only use the right files.
- See every model you have: `ollama list`.
- Try a different model: copy any `ollama run` name from the Models page.
- Update your model: run `ollama pull {MODEL}` again. It only downloads what changed.
- Free disk space: `ollama rm {MODEL}` deletes a model you no longer use.

## Windows / Linux (not tested by us)

Install Ollama with this PowerShell command, or the installer from ollama.com/download. On Linux, the install command above works as it is. After that, every `ollama` command on this page is the same. Open WebUI and Docling also run on Windows; their pages have the steps.

```powershell
irm https://ollama.com/install.ps1 | iex
```
(Windows: paste in PowerShell. Or get the installer from ollama.com/download)


---

# Recipe: Speech to text

Accurate speech-to-text for meetings, interviews and voice notes, without sending audio anywhere.

URL: https://insidethemachine.ai/do/voice
Memory: needs 8 GB+, best with 16 GB+. Platform: macOS (Apple silicon) first.
Run end to end on an Apple M4 Mac with 16 GB on 2026-10-15.

## Voice model (replace {WHISPER})

- under 16 GB: base.en
- 16 GB+: large-v3-turbo

## Steps

1. **Install the build tools**: whisper.cpp is built on your computer. These tools do that. Skip the first line if you already have it.
   ```sh
   xcode-select --install
   ```
   ```sh
   brew install cmake ffmpeg
   ```
   (Needs Homebrew (brew.sh))
2. **Get whisper.cpp and a voice model**: The voice model turns sound into words.
   ```sh
   git clone https://github.com/ggml-org/whisper.cpp.git && cd whisper.cpp
   ```
   ```sh
   sh ./models/download-ggml-model.sh {WHISPER}
   ```
3. **Build it**: This takes a minute or two.
   ```sh
   cmake -B build && cmake --build build -j --config Release
   ```
4. **Test it**: It comes with a short sample speech.
   ```sh
   ./build/bin/whisper-cli -m models/ggml-{WHISPER}.bin -f samples/jfk.wav
   ```
   Expect: It prints the words of the sample speech.
5. **Use your own audio**: whisper.cpp reads 16-bit WAV files. Convert your file first, then transcribe it to a text file.
   ```sh
   ffmpeg -i input.m4a -ar 16000 -ac 1 -c:a pcm_s16le output.wav
   ```
   ```sh
   ./build/bin/whisper-cli -m models/ggml-{WHISPER}.bin -f output.wav -otxt
   ```
   Expect: output.wav.txt has your transcript.

## Alternative

Want to dictate instead? Use Handy. Handy is a free app. Hold a key, talk, and your words are typed into any app. It runs offline. Download it from handy.computer. (https://insidethemachine.ai/setups/handy)

## Rollback

- `cd .. && rm -rf whisper.cpp` (Removes the code, the build and the voice model)
- `brew uninstall cmake` (Only if you installed it for this)

## One-command install

```bash
curl -fsSL https://insidethemachine.ai/install/voice.sh | bash             # install, then check
curl -fsSL https://insidethemachine.ai/install/voice.sh | bash -s -- plan     # print only
curl -fsSL https://insidethemachine.ai/install/voice.sh | bash -s -- rollback --yes
```

Run status and Windows: https://insidethemachine.ai/install/voice.md. The script picks {MODEL} from the machine's memory (override: ITM_RAM, ITM_MODEL).

## Notes

- Needs about 2 GB of free disk space.
- Models ending in .en are English only and a bit faster.
- On a 16 GB M4 Mac, a short clip took under 2 seconds.
- Long files take time. A Mac with more memory can use the bigger, more accurate model.

## If something goes wrong

- An “xcrun: error” when you build: The build tools are missing. Run `xcode-select --install` again and finish the window that opens.
- “cmake: command not found”: Run `brew install cmake`, then build again.
- It cannot read your audio file: whisper.cpp needs a 16-bit WAV file. Convert your file with the ffmpeg line in step 5 first.

## After it works

- Try it: record a voice note on your phone, send it to your Mac, convert it and transcribe it.
- Want subtitles? Add `-osrt` to the whisper-cli line to make a subtitle file.
- For typing by voice in any app, try Handy (the box above).

## Windows / Linux (not tested by us)

On Linux, the same steps work. Install cmake and ffmpeg with your package manager instead of brew. On Windows, the Handy app (handy.computer) is the easiest way to start.



---

# Recipe: Make images

Pictures from a text prompt, made on your own computer. No credits, no upload.

URL: https://insidethemachine.ai/do/images
Memory: needs 16 GB+, best with 32 GB+. Platform: macOS (Apple silicon) first.
Not yet tested on our Mac Studio. Both are apps; follow the app's own instructions if a screen looks different.

## Steps

1. **Easiest: install Draw Things**: Draw Things is a free Mac app made for Apple silicon. Get it from the Mac App Store.

   Link: https://drawthings.ai
2. **Pick a model**: When it opens, choose a model from its list and let it download. Pick a smaller one first. A small model is faster and still looks good.

   Expect: The model shows as ready.
3. **Make your first image**: Type what you want to see, then press Generate. Short, concrete prompts work best, for example “a red bicycle in the rain, photo”.

   Expect: An image appears after a short wait.
4. **Want more control? Try ComfyUI**: ComfyUI builds images from connected blocks. It can do much more, but it takes longer to learn. Download the desktop app from comfy.org and start from one of its templates.

   Link: https://insidethemachine.ai/setups/comfyui

## One-command install

```bash
curl -fsSL https://insidethemachine.ai/install/images.sh | bash             # install, then check
curl -fsSL https://insidethemachine.ai/install/images.sh | bash -s -- plan     # print only
curl -fsSL https://insidethemachine.ai/install/images.sh | bash -s -- rollback --yes
```

Run status and Windows: https://insidethemachine.ai/install/images.md. The script picks {MODEL} from the machine's memory (override: ITM_RAM, ITM_MODEL).

## Notes

- Image models use a lot of memory. 16 GB works. 32 GB or more is faster and fits the best models.
- These are apps, so there are no Terminal commands to copy here.

## If something goes wrong

- It is very slow: Pick a smaller model and a smaller image size. Close other big apps.
- “out of memory” in ComfyUI: The model is too big for your memory. Pick a smaller model or lower the image size.

## After it works

- Try it: make the same prompt three times. Each image is different. Keep the one you like.
- Add a style to your prompt, for example “watercolour” or “pencil sketch”.
- Image models are big. Delete the ones you do not use in the app to free disk space.

## Windows / Linux (not tested by us)

Draw Things is Mac only. On a Windows PC with an NVIDIA graphics card, use the ComfyUI desktop app from comfy.org. Pick its models by your graphics card's memory.



---

# Recipe: An agent that does tasks

A personal AI agent that remembers you, uses tools, learns skills and can chat with you from your phone.

URL: https://insidethemachine.ai/do/agent
Memory: needs 32 GB+, best with 64 GB+. Platform: macOS (Apple silicon) first.
Commands checked against each tool's official docs on 2026-10-15. Not yet run end to end on our Mac Studio.

## Model by memory (replace {MODEL})

| RAM GB | model | ollama tag | needs GB |
|---|---|---|---|
| 8 | Qwen3.5 4B | qwen3.5:4b | 5.8 |
| 16 | Gemma 4 12B | gemma4:12b | 11.2 |
| 24 | Gemma 4 12B | gemma4:12b | 11.2 |
| 32 | Qwen3.8 27B | qwen3.8:27b | 22.7 |
| 48 | Qwen3.8 27B | qwen3.8:27b | 22.7 |
| 64 | Qwen3.8 27B | qwen3.8:27b | 22.7 |
| 96 | Qwen3.8 27B | qwen3.8:27b | 22.7 |
| 128 | Qwen3.8 27B | qwen3.8:27b | 22.7 |
| 192 | Qwen3.8-Flash-Next (125B-A6B) | qwen3.8-flash-next:125b-a6b | 140 |
| 256 | Qwen3.8-Flash-Next (125B-A6B) | qwen3.8-flash-next:125b-a6b | 140 |
| 512 | Qwen3.8-Flash-Next (125B-A6B) | qwen3.8-flash-next:125b-a6b | 140 |

## Steps

1. **Install Ollama**: Ollama downloads AI models and runs them on your computer. Open the Terminal app and paste this. It may ask for your Mac password.
   ```sh
   curl -fsSL https://ollama.com/install.sh | sh
   ```
   (Or download the app from ollama.com/download)
   Expect: Run `ollama --version`. It prints a version number. If it also says “could not connect”, open Ollama from your Applications folder, wait a few seconds, then go on.
2. **Download your model**: This is the AI itself. It is one big file, so it takes a few minutes.
   ```sh
   ollama pull {MODEL}
   ```
   Expect: The download finishes with “success”.
3. **Give the model a long memory**: Agents read a lot at once. Quit the Ollama menu-bar app, then start Ollama like this. Leave this window open.
   ```sh
   OLLAMA_CONTEXT_LENGTH=64000 ollama serve
   ```
4. **Install Hermes Agent**: In a second Terminal window, this one command installs Hermes and connects it to your model. If it asks for a model, pick {MODEL}.
   ```sh
   ollama launch hermes
   ```
   Expect: Run `hermes doctor`. It shows no blocking errors.
5. **Talk to it**: Start Hermes and give it a small job.
   ```sh
   hermes
   ```
   Expect: It answers, and it remembers what you said next time.
6. **Optional: chat from your phone**: Hermes can connect to Telegram, Discord, Slack, WhatsApp, Signal or email.
   ```sh
   hermes gateway setup
   ```

## Alternative

Next: give it more tools MCP servers are plug-ins that let an agent use files, git, the web and more. Start with the official ones. (https://insidethemachine.ai/setups/mcp-servers)

## Rollback

- `hermes uninstall` (Keeps your data in ~/.hermes. Add --full to remove it too.)
- `ollama rm {MODEL}`

## One-command install

```bash
curl -fsSL https://insidethemachine.ai/install/agent.sh | bash             # install, then check
curl -fsSL https://insidethemachine.ai/install/agent.sh | bash -s -- plan     # print only
curl -fsSL https://insidethemachine.ai/install/agent.sh | bash -s -- rollback --yes
```

Run status and Windows: https://insidethemachine.ai/install/agent.md. The script picks {MODEL} from the machine's memory (override: ITM_RAM, ITM_MODEL).

## Notes

- Agents need more memory than chat because they read long instructions every turn. 64 GB is comfortable.
- Hermes changes fast. If a command fails, check its docs.

## If something goes wrong

- “could not connect to ollama app, is it running?”: Ollama is not running. Open Ollama from your Applications folder, or run `ollama serve` in a new Terminal window and leave it open.
- “command not found: ollama”: Close the Terminal window and open a new one. If it still fails, run the install command again.
- “model requires more system memory”: The model is too big for your memory. Pick a smaller memory size at the top of this page and use that model. Close other big apps too.
- “file does not exist” when you download: The model name is wrong, or Ollama is too old. Copy the command again from this page. Then update Ollama: run the install command again.
- It is very slow: Run `ollama ps`. PROCESSOR should say 100% GPU. If it shows CPU, the model does not fit in memory. Pick a smaller model.
- The computer freezes, or the fan is loud: The model uses all your memory. Stop it with `ollama stop {MODEL}`. Then use a smaller one.
- “hermes: command not found”: Close the Terminal window and open a new one. Then try again.
- It forgets the start of a long job: Ollama was started without the long memory. Quit Ollama and run step 3 again.

## After it works

- Try it: tell it your name and one thing you like. Close it, open it again, and ask what it remembers.
- Give it one small job a day, for example “sort the files in my Downloads folder”. Check what it did.
- See every model you have: `ollama list`.
- Try a different model: copy any `ollama run` name from the Models page.
- Update your model: run `ollama pull {MODEL}` again. It only downloads what changed.
- Free disk space: `ollama rm {MODEL}` deletes a model you no longer use.

## Windows / Linux (not tested by us)

Install Ollama with this PowerShell command, or the installer from ollama.com/download. On Linux, the install command above works as it is. After that, every `ollama` command on this page is the same. In PowerShell, start Ollama with a long memory like this. Hermes Agent's page has its Windows install line.

```powershell
irm https://ollama.com/install.ps1 | iex
```
(Windows: paste in PowerShell. Or get the installer from ollama.com/download)
```powershell
$env:OLLAMA_CONTEXT_LENGTH=64000; ollama serve
```
(PowerShell version of step 3)


---

# Harnesses for local models

Agent and app harnesses (coding agents, personal agents, and tool-using chat apps) that can drive a model running on your own machine, with the exact way to connect each one.
Data: 2026-10-15. JSON: /harnesses.json

## Which harness for which job

| job | app | min memory GB | recipe |
|---|---|---|---|
| Write code | opencode at 32 GB+, aider below | 8 | /do/code.md |
| Chat privately | open-webui | 8 | /do/chat.md |
| Text an assistant from my phone | openclaw | 32 | /setups/openclaw.md |
| An agent that remembers me | hermes-agent | 32 | /do/agent.md |

Model per memory size: the recipe pages list it (/do/code.md, /do/chat.md, /do/agent.md).

## Claude Code vs Codex with local models

- claude-code: Made by: Anthropic; Open source: No; Start it with a local model: ollama launch claude; Pick it if: You already use Claude Code and want the same commands, skills and workflow on your own computer.
- codex-cli: Made by: OpenAI; Open source: Yes; Start it with a local model: ollama launch codex; Pick it if: You want an official local mode (the --oss flag), or you run OpenAI's own open model, gpt-oss.
- Both need 64K context and a tool-calling model (about 32 GB of memory or more).

## Why the harness matters

- On the Terminal-Bench 2.1 leaderboard, Gemini 3 Pro scores 73.9% in the Terminus 2 harness but 65.8% in Gemini CLI, and GPT-5.5 scores 83.1% in Codex CLI but 78% in Terminus 2. (Snorkel AI, Terminal-Bench 2.1 leaderboard, https://snorkel.ai/leaderboard/terminal-bench-2-1/, retrieved 2026-10-15)
- LangChain changed only its harness (prompt, tools, middleware) and kept the model fixed at gpt-5.2-codex; its Terminal Bench 2.0 score rose 13.7 points, from 52.8 to 66.5. (LangChain blog, Improving Deep Agents with harness engineering (2026-02-17), https://www.langchain.com/blog/improving-deep-agents-with-harness-engineering, retrieved 2026-10-15)
- Across 66 model and harness pairings, model rankings flip by harness: on Terminal-Bench 4, Claude leads GPT by 7.94 points in OpenHands but trails it by 30.16 points in Pi. (arXiv 2610.00917, Finding the Right Fit: Model-Harness Interactions across Agent Tasks, https://arxiv.org/abs/2610.00917, retrieved 2026-10-15)
- With a small 20,480-token context on SWE-bench Verified, a harness that only trims old tool output and reacts to stalled work raised fully solved tasks from 43 to 72 with the same model. (arXiv 2608.26218, Same Model, Different Harness: Different Coding-Agent Results, https://arxiv.org/abs/2608.26218, retrieved 2026-10-15)

## List

| name | kind | interface | local models | how to connect | ease | needs tool calling | min context | license |
|---|---|---|---|---|---|---|---|---|
| OpenCode | coding | terminal | native | `ollama launch opencode` | 1 | true | 64000 | MIT |
| Pi (pi-mono) | coding | terminal | openai-compatible | `Add a provider to models.json with "baseUrl": "http://localhost:11434/v1" and "api": "openai-completions"` | 2 | true | unknown | MIT |
| Cline | coding | IDE extension | native | `Pick provider "Ollama" with Base URL http://localhost:11434, then enable "Use Compact Prompt"` | 1 | unknown | unknown | Apache-2.0 |
| Aider | coding | terminal | native | `export OLLAMA_API_BASE=http://127.0.0.1:11434 then aider --model ollama_chat/<model>` | 2 | false | unknown | Apache-2.0 |
| Kilo Code | coding | IDE extension | native | `Settings > Providers > add Ollama (no API key), then set "Context Window Size (num_ctx)"` | 1 | true | 32000 | MIT |
| Goose | coding | desktop app | native | `goose configure > Configure Providers > Ollama (defaults to localhost:11434)` | 1 | true | unknown | Apache-2.0 |
| Continue | coding | IDE extension | native | `In config.yaml: provider: ollama, model: <name from ollama list>, apiBase: http://localhost:11434` | 2 | true | unknown | Apache-2.0 |
| Crush | coding | terminal | native | `provider add ollama --name Ollama --type ollama --base-url "http://localhost:11434/v1/"` | 2 | unknown | unknown | FSL-1.1-MIT |
| Qwen Code | coding | terminal | openai-compatible | `In settings.json add a modelProviders.openai entry with "baseUrl": "http://localhost:11434/v1" and a contextWindowSize` | 2 | unknown | unknown | Apache-2.0 |
| Zed | coding | desktop app | native | `In settings set the Ollama "api_url": "http://localhost:11434"; Zed discovers pulled models` | 1 | unknown | unknown | GPL-3.0-or-later |
| Codex CLI | coding | terminal | native | `ollama launch codex or codex --oss -m gpt-oss:120b` | 1 | unknown | 64000 | Apache-2.0 |
| Claude Code | coding | terminal | config | `ollama launch claude (or export ANTHROPIC_BASE_URL=http://localhost:11434 with ANTHROPIC_AUTH_TOKEN=ollama)` | 1 | true | 64000 | unknown |
| OpenHands | coding | web app | openai-compatible | `Base URL http://host.docker.internal:11434/v1, Custom Model openai/qwen3.6:35b-a3b, any API key` | 2 | unknown | 22000 | MIT |
| DeepSeek Harness | coding | web app | native | `ollama launch dsh` | 2 | unknown | unknown | MIT |
| Open Interpreter | coding | terminal | native | `Built-in "Ollama local OSS" and "LM Studio local OSS" providers; switch with /model` | 2 | unknown | unknown | Apache-2.0 |
| llama.vscode | coding | IDE extension | native | `Install the extension, use its "Install/Upgrade llama.cpp" menu option, then pick a local model` | 1 | unknown | unknown | MIT |
| mini-SWE-agent | coding | terminal | config | `In the model config set model_kwargs: api_base: "http://localhost:8000/v1" (passed to LiteLLM)` | 3 | unknown | unknown | MIT |
| Gemini CLI | coding | terminal | no | - | 3 | unknown | unknown | Apache-2.0 |
| OpenClaw | general | messaging | native | `ollama launch openclaw` | 1 | true | 64000 | MIT |
| Hermes Agent | general | terminal | native | `ollama launch hermes` | 1 | true | 64000 | MIT |
| nanobot | general | messaging | native | `In config: "providers": { "ollama": { "apiBase": "http://localhost:11434/v1" } }` | 2 | unknown | unknown | MIT |
| LM Studio Bionic | general | desktop app | native | - | 1 | unknown | unknown | unknown |
| Vane (Perplexica) | general | web app | native | `In settings set the Ollama API URL to http://host.docker.internal:11434` | 1 | unknown | unknown | MIT |
| Browser Use | general | terminal | native | `llm = ChatOllama(model="llama3.1:8b")` | 3 | unknown | unknown | MIT |
| GPT Researcher | general | web app | native | `In .env: OLLAMA_BASE_URL="http://127.0.0.1:11434/" and FAST_LLM="ollama:<model>"` | 2 | unknown | unknown | Apache-2.0 |
| Khoj | general | web app | openai-compatible | `export OPENAI_BASE_URL="http://localhost:11434/v1/" then khoj --anonymous-mode` | 2 | unknown | unknown | AGPL-3.0 |
| UI-TARS Desktop | general | desktop app | openai-compatible | `Settings > VLM Base URL: an OpenAI-compatible endpoint (for example vLLM) serving a UI-TARS model` | 3 | unknown | unknown | Apache-2.0 |
| DeerFlow | general | web app | openai-compatible | `Add a model in config.yaml with use: langchain_openai:ChatOpenAI and a local base_url (vLLM example: http://localhost:8000/v1)` | 3 | unknown | unknown | MIT |
| Open WebUI | chat | web app | native | `pip install open-webui && open-webui serve (finds Ollama at http://localhost:11434)` | 1 | true | unknown | unknown |
| LM Studio | chat | desktop app | native | `Runs models itself; add tools via Program tab > Install > Edit mcp.json` | 1 | unknown | unknown | unknown |
| Jan | chat | desktop app | native | `Built-in llama.cpp and MLX engines; download a model in the app` | 1 | unknown | unknown | Apache-2.0 |
| AnythingLLM | chat | desktop app | native | `Choose Ollama in LLM settings with base URL http://127.0.0.1:11434; start agents with @agent` | 1 | unknown | unknown | MIT |
| Cherry Studio | chat | desktop app | native | `Enable the built-in Ollama or LM Studio provider in settings` | 1 | unknown | unknown | AGPL-3.0 |
| LobeHub (LobeChat) | chat | web app | native | `docker run -d -p 3210:3210 -e OLLAMA_PROXY_URL=http://host.docker.internal:11434 lobehub/lobehub` | 2 | unknown | unknown | unknown |
| LibreChat | chat | web app | openai-compatible | `In librechat.yaml add a custom endpoint named "Ollama" with baseURL: "http://localhost:11434/v1/"` | 2 | unknown | unknown | MIT |
| GitHub Copilot CLI | coding | terminal | native | `/model in Copilot CLI 1.0.94-0 or later lists models from a running Ollama; pick one, then Add and use for this session` | 1 | true | unknown | unknown |


---

# Start here: local AI in plain words

URL: https://insidethemachine.ai/start-here

## Three parts
- Model: the AI itself. One big file you download. It holds what the AI learned.
- Ollama: the engine. It loads the model and runs it on your computer. Free.
- App: the window you talk to (Open WebUI, LM Studio, OpenCode, Hermes). It sends your words to Ollama and shows the answer.
All three run on your computer. Nothing goes to the internet after the download.

## Memory decides which models fit
The whole model must fit in memory while it runs. On a Mac about 75% of memory is usable for models. On a PC with a graphics card, the card's own memory (VRAM) counts, not the computer's RAM.
- 8 GB computer (~6 GB usable): Qwen3.5 4B, needs ~5.8 GB, about 23% as smart as Claude Opus 5.5
- 16 GB computer (~12 GB usable): K2 Horizon 7B, needs ~8.6 GB, about 36% as smart as Claude Opus 5.5
- 32 GB computer (~24 GB usable): Qwen3.8 27B, needs ~22.7 GB, about 59% as smart as Claude Opus 5.5
Find your memory: Mac: Apple menu > About This Mac. Windows: Settings > System > About > Installed RAM. Graphics card: Task Manager > Performance > GPU > Dedicated GPU memory.

## What "27B" means
B = billion. A 27B model has 27 billion numbers it learned. More numbers: smarter, bigger file, slower. Example: Qwen3.8 27B is a 27B model; its Q4 file is 18 GB and it needs ~22.7 GB of memory with room for the chat.
"36B-A4B" = 36 billion numbers in total, only 4 billion used for each word. It needs the memory of a 36B model but runs at the speed of a 4B model.

## Speed
Speed is tokens per second (tok/s). People read at about 5 tok/s.
- Under 10 tok/s: about reading speed or slower. Example: llama3.2 3B on a Raspberry Pi 5 (CPU only): 5.6 tok/s.
- 10 to 40 tok/s: comfortable.
- 40+ tok/s: faster than you can read. Example: gpt-oss-20b on an M5 Pro Mac: 76.6 tok/s.
Memory bandwidth (GB/s) sets speed. The first answer is slow while the model loads.

## How smart
We compare each model with Claude Opus 5.5, the best paid AI, on the Artificial Analysis Intelligence Index. 100% = as smart as Claude Opus 5.5.

## Is it safe?
- The install command downloads Ollama's official script from ollama.com and runs it. Only run commands from sites you trust; you can open the script URL in a browser to read it first.
- Ollama only listens on your own computer (127.0.0.1:11434) unless you change it.
- Test: after the download, turn off Wi-Fi. It still answers.
- Models come from the Ollama library or Hugging Face. Check the licence before business use.

## Words
- Token: A piece of a word. 100 tokens is about 75 English words.
- Context: How much text the model can read at once: your chat, files and instructions. More context needs more memory.
- Q4 (4-bit): A smaller copy of a model. It keeps most of the smarts and needs less than a third of the space. The sizes on this site are Q4.
- Open weights: The maker lets you download the model file. Check its licence before you use it for business.
- Harness: Another word for the app around the model. It can read files, use tools and remember things.
- GPU: The part of the computer that does the maths fast. On a Mac it shares the normal memory. On a PC it is the graphics card.

Next: pick a goal at https://insidethemachine.ai/#goals