---
slug: hermes-agent
kind: runbook
status: docs-checked
sh: https://insidethemachine.ai/install/hermes-agent.sh
ps1: https://insidethemachine.ai/install/hermes-agent.ps1
json: https://insidethemachine.ai/install/hermes-agent.json
page: https://insidethemachine.ai/setups/hermes-agent
---

# Install: Hermes Agent

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

**Run status: Not run: commands checked against the official docs only.** Commands checked against the official docs on 2026-10-15. Not run end to end.

**This script:** 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.

## One command

```bash
curl -fsSL https://insidethemachine.ai/install/hermes-agent.sh | bash
```

Windows (PowerShell):

```powershell
irm https://insidethemachine.ai/install/hermes-agent.ps1 | iex
```

Actions: `| bash -s -- plan` (print only), `verify`, `rollback --yes`. Env: ITM_RAM. Read the script first: `curl -fsSL https://insidethemachine.ai/install/hermes-agent.sh | less`.

Lines marked YOU RUN are not run by the script (servers, interactive apps, your own files). The script prints them at the end, in order.

## Steps

### macOS

Install:

1. **Install Hermes Agent**
   - run: `curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash`
   - YOU RUN (open a new Terminal window instead): `source ~/.zshrc`
2. **Configure (your choices)**
   - YOU RUN (easiest path: Ollama installs Hermes if needed, points it at http://127.0.0.1:11434/v1 and sets your model as primary): `ollama launch hermes`
   - YOU RUN (manual path: choose More providers → Custom endpoint → http://127.0.0.1:11434/v1, leave API key blank): `hermes model`
   - YOU RUN (Ollama docs: agents need at least 64000 tokens of context): `OLLAMA_CONTEXT_LENGTH=64000 ollama serve`
   - YOU RUN (optional: chat with it from Telegram/Discord/Slack/WhatsApp/Signal/Email): `hermes gateway setup`

Verify:

- `hermes doctor` → expect: diagnostics report with no blocking errors
- by hand: `hermes` → expect: TUI opens; a one-line prompt gets an answer from the local model

Rollback:

- run: `hermes uninstall --dry-run`
- run: `hermes uninstall`

### Linux

Install:

1. **Install Hermes Agent**
   - run: `curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash`
   - note: Open a new Terminal window (or run: source ~/.bashrc)
2. **Configure (your choices)**
   - YOU RUN (easiest path: Ollama installs Hermes if needed, points it at http://127.0.0.1:11434/v1 and sets your model as primary): `ollama launch hermes`
   - YOU RUN (manual path: choose More providers → Custom endpoint → http://127.0.0.1:11434/v1, leave API key blank): `hermes model`
   - YOU RUN (Ollama docs: agents need at least 64000 tokens of context): `OLLAMA_CONTEXT_LENGTH=64000 ollama serve`
   - YOU RUN (optional: chat with it from Telegram/Discord/Slack/WhatsApp/Signal/Email): `hermes gateway setup`

Verify:

- `hermes doctor` → expect: diagnostics report with no blocking errors
- by hand: `hermes` → expect: TUI opens; a one-line prompt gets an answer from the local model

Rollback:

- run: `hermes uninstall --dry-run`
- run: `hermes uninstall`

### Windows (PowerShell, not run by us)

Install:

1. **Install Hermes Agent**
   - run: `iex (irm https://hermes-agent.nousresearch.com/install.ps1)`

Verify:

- `hermes doctor` → expect: diagnostics report with no blocking errors
- by hand: `hermes` → expect: TUI opens; a one-line prompt gets an answer from the local model

Rollback:

- run: `hermes uninstall --dry-run`
- run: `hermes uninstall`