Hermes

Hermes is an autonomous AI agent from Nous Research that lives on your server. It speaks the OpenAI API format, so you can point it at Router9 by adding a custom endpoint — no code changes required.

Setup

Hermes stores its model configuration in ~/.hermes/config.yaml. Add a custom OpenAI-compatible endpoint under the model: block:

model:
  provider: custom
  name: gpt-4o
  base_url: https://api.router9.com/v1
  api_mode: openai

When provider is set to custom, Hermes calls base_url directly and authenticates with OPENAI_API_KEY.

API Key

Put your Router9 key in ~/.hermes/.env:

OPENAI_API_KEY=sk-r9k-your-key-here

Or set it with the CLI, which routes the value to the right file automatically:

hermes config set OPENAI_API_KEY sk-r9k-your-key-here

Choosing Models

The name field is the model id Router9 routes on. Swap it for any model Router9 supports:

model:
  provider: custom
  name: claude-sonnet-4-20250514
  base_url: https://api.router9.com/v1
  api_mode: openai

Other ids include gpt-4o-mini and gpt-4o.

Using the Anthropic Endpoint

For Anthropic-native model access, Router9 also provides an Anthropic-compatible endpoint. Point the base_url at it and switch the request format:

model:
  provider: custom
  name: claude-sonnet-4-20250514
  base_url: https://api.router9.com/anthropic
  api_mode: anthropic

See the Anthropic API reference for details.

Tips

• Router9's flat monthly pricing pairs well with long-running agent sessions — no per-token cost surprises.
• Hermes can expose itself as an OpenAI-compatible API server, so Router9 also backs any frontend you connect to Hermes (Open WebUI, LibreChat, and others).
• Keep your key in ~/.hermes/.env rather than committing it to config.yaml.