Hermes Agent

---
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