{ "kind": "recipe", "id": "code", "title": "A coding helper", "what": "An assistant that reads and edits your code.", "html": "https://insidethemachine.ai/do/code", "md": "https://insidethemachine.ai/do/code.md", "json": "https://insidethemachine.ai/do/code.json", "memory": { "min_gb": 16, "good_gb": 32 }, "minutes": 15, "platform_priority": [ "macos-apple-silicon", "linux", "windows" ], "tools": [ { "slug": "ollama", "name": "Ollama", "md": "https://insidethemachine.ai/setups/ollama.md" }, { "slug": "opencode", "name": "OpenCode", "md": "https://insidethemachine.ai/setups/opencode.md" }, { "slug": "aider", "name": "Aider", "md": "https://insidethemachine.ai/setups/aider.md" } ], "placeholders": { "{MODEL}": "ollama tag from model_by_memory_gb for the machine's RAM", "{WHISPER}": null }, "model_by_memory_gb": { "8": { "name": "Qwen3.5 4B", "tag": "qwen3.5:4b", "gb": 5.8, "aa": 13.1, "maker": "Alibaba Qwen" }, "16": { "name": "Ornith 1.5 9B", "tag": "ornith-1.5:9b", "gb": 8.8, "aa": null, "maker": "Ornith AI" }, "24": { "name": "Gemma 4 12B", "tag": "gemma4:12b", "gb": 11.2, "aa": 14.2, "maker": "Google" }, "32": { "name": "Qwen3.8 27B", "tag": "qwen3.8:27b", "gb": 22.7, "aa": 33.7, "maker": "Alibaba Qwen" }, "48": { "name": "Qwen3.8 27B", "tag": "qwen3.8:27b", "gb": 22.7, "aa": 33.7, "maker": "Alibaba Qwen" }, "64": { "name": "Qwen3.8 27B", "tag": "qwen3.8:27b", "gb": 22.7, "aa": 33.7, "maker": "Alibaba Qwen" }, "96": { "name": "Qwen3.8 27B", "tag": "qwen3.8:27b", "gb": 22.7, "aa": 33.7, "maker": "Alibaba Qwen" }, "128": { "name": "Qwen3.8 27B", "tag": "qwen3.8:27b", "gb": 22.7, "aa": 33.7, "maker": "Alibaba Qwen" }, "192": { "name": "Qwen3.8-Flash-Next (125B-A6B)", "tag": "qwen3.8-flash-next:125b-a6b", "gb": 140, "aa": 39.8, "maker": "Alibaba Qwen" }, "256": { "name": "Qwen3.8-Flash-Next (125B-A6B)", "tag": "qwen3.8-flash-next:125b-a6b", "gb": 140, "aa": 39.8, "maker": "Alibaba Qwen" }, "512": { "name": "Qwen3.8-Flash-Next (125B-A6B)", "tag": "qwen3.8-flash-next:125b-a6b", "gb": 140, "aa": 39.8, "maker": "Alibaba Qwen" } }, "frontier": { "name": "Claude Opus 5.5", "aa": 57.6 }, "tested": "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.", "recipe": { "id": "code", "get": "An AI coding agent in your Terminal that reads your project, edits files and runs commands, with changes you can undo.", "model": "code", "steps": [ { "title": "Install Ollama", "body": "Ollama downloads AI models and runs them on your computer. Open the Terminal app and paste this. It may ask for your Mac password.", "cmds": [ { "run": "curl -fsSL https://ollama.com/install.sh | sh", "note": "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." }, { "title": "Download a coding model", "body": "This is the AI itself. It is one big file, so it takes a few minutes.", "cmds": [ { "run": "ollama pull {MODEL}" } ], "expect": "The download finishes with “success”." }, { "title": "Give the model a long memory", "body": "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.", "cmds": [ { "run": "OLLAMA_CONTEXT_LENGTH=64000 ollama serve" } ] }, { "title": "Install OpenCode", "body": "OpenCode is the coding agent. Open a second Terminal window.", "cmds": [ { "run": "curl -fsSL https://opencode.ai/install | bash", "note": "Or with Homebrew: brew install anomalyco/tap/opencode" } ], "expect": "Run `opencode --version`. It prints a version." }, { "title": "Start it in your project", "body": "Go to your project folder, then let Ollama start OpenCode. When it asks for a model, pick {MODEL}.", "cmds": [ { "run": "cd /path/to/your/project" }, { "run": "ollama launch opencode" } ], "expect": "Ask “explain this project”. It answers about your files." } ], "alt": { "slug": "aider", "title": "Prefer a simpler helper? Use Aider.", "body": "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.", "href": "/setups/aider" }, "lowRam": { "under": 32, "why": "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.", "steps": [ { "title": "Install Ollama", "body": "Ollama downloads AI models and runs them on your computer. Open the Terminal app and paste this. It may ask for your Mac password.", "cmds": [ { "run": "curl -fsSL https://ollama.com/install.sh | sh", "note": "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." }, { "title": "Download a coding model", "body": "This is the AI itself. It is one big file, so it takes a few minutes.", "cmds": [ { "run": "ollama pull {MODEL}" } ], "expect": "The download finishes with “success”." }, { "title": "Give the model more room", "body": "Code needs a longer memory than chat. Quit the Ollama menu-bar app, then start Ollama like this. Leave this window open.", "cmds": [ { "run": "OLLAMA_CONTEXT_LENGTH=8192 ollama serve" } ] }, { "title": "Install Aider", "body": "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.", "cmds": [ { "run": "brew install uv", "note": "Needs Homebrew (brew.sh)" }, { "run": "uv tool install --force --python python3.12 --with pip aider-chat@latest" } ], "expect": "Run `aider --version`. It prints a version." }, { "title": "Start it in your project", "body": "Go to a project folder that uses git, then start Aider with your model.", "cmds": [ { "run": "export OLLAMA_API_BASE=http://127.0.0.1:11434" }, { "run": "cd /path/to/your/project" }, { "run": "aider --model ollama_chat/{MODEL}" } ], "expect": "Ask “explain this project”. It answers about your files." } ], "alt": { "slug": "opencode", "title": "Have 32 GB or more? Use OpenCode.", "body": "OpenCode is the most popular open-source coding agent. It needs a model that can use tools and 64k of context, so it needs more memory.", "href": "/setups/opencode" }, "undo": [ { "run": "uv tool uninstall aider-chat", "note": "Removes Aider" }, { "run": "ollama rm {MODEL}" } ], "win": { "body": "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.", "cmds": [ { "run": "irm https://ollama.com/install.ps1 | iex", "note": "Windows: paste in PowerShell. Or get the installer from ollama.com/download" }, { "run": "$env:OLLAMA_CONTEXT_LENGTH=8192; ollama serve", "note": "PowerShell version of step 3" } ] }, "fix": [ { "q": "“could not connect to ollama app, is it running?”", "a": "Ollama is not running. Open Ollama from your Applications folder, or run `ollama serve` in a new Terminal window and leave it open." }, { "q": "“command not found: ollama”", "a": "Close the Terminal window and open a new one. If it still fails, run the install command again." }, { "q": "“model requires more system memory”", "a": "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." }, { "q": "“file does not exist” when you download", "a": "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." }, { "q": "It is very slow", "a": "Run `ollama ps`. PROCESSOR should say 100% GPU. If it shows CPU, the model does not fit in memory. Pick a smaller model." }, { "q": "The computer freezes, or the fan is loud", "a": "The model uses all your memory. Stop it with `ollama stop {MODEL}`. Then use a smaller one." }, { "q": "A warning about “unknown context window size”", "a": "You can ignore it. Aider still works with your model." }, { "q": "“aider: command not found”", "a": "Close the Terminal window and open a new one. If it still fails, run `uv tool update-shell` and open a new window." } ], "know": [ "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." ] }, "undo": [ { "run": "rm -rf ~/.opencode", "note": "Removes OpenCode from the install script. Also delete the line with .opencode/bin in ~/.zshrc. With Homebrew: brew uninstall opencode" }, { "run": "ollama rm {MODEL}" } ], "know": [ "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." ], "fix": [ { "q": "“could not connect to ollama app, is it running?”", "a": "Ollama is not running. Open Ollama from your Applications folder, or run `ollama serve` in a new Terminal window and leave it open." }, { "q": "“command not found: ollama”", "a": "Close the Terminal window and open a new one. If it still fails, run the install command again." }, { "q": "“model requires more system memory”", "a": "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." }, { "q": "“file does not exist” when you download", "a": "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." }, { "q": "It is very slow", "a": "Run `ollama ps`. PROCESSOR should say 100% GPU. If it shows CPU, the model does not fit in memory. Pick a smaller model." }, { "q": "The computer freezes, or the fan is loud", "a": "The model uses all your memory. Stop it with `ollama stop {MODEL}`. Then use a smaller one." }, { "q": "It talks, but it does not change any files", "a": "The model is too small to use tools. Use a bigger model, or Aider (the box above), which does not need tools." }, { "q": "It forgets the start of the job", "a": "Ollama was started without the long memory. Quit Ollama and run step 3 again." } ], "after": [ "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." ], "win": { "body": "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.", "cmds": [ { "run": "irm https://ollama.com/install.ps1 | iex", "note": "Windows: paste in PowerShell. Or get the installer from ollama.com/download" }, { "run": "$env:OLLAMA_CONTEXT_LENGTH=64000; ollama serve", "note": "PowerShell version of step 3" } ] }, "tested": "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." } }