GatewayCoding Agents

Hermes Agent (gateway)

Route Hermes Agent’s LLM calls through the Respan gateway for automatic logging, caching, and model switching. Hermes talks to any OpenAI-compatible endpoint, so only your RESPAN_API_KEY is needed.

Setup

1

Install Hermes Agent

npm install -g hermes-agent
2

Point Hermes at the Respan gateway

Edit ~/.hermes/config.yaml and set a custom OpenAI-compatible provider:

model:
  default: gpt-4o
  provider: custom
  base_url: "https://api.respan.ai/api"
  api_key: "YOUR_RESPAN_API_KEY"

Or set the same values as environment variables in ~/.hermes/.env:

OPENAI_BASE_URL=https://api.respan.ai/api
OPENAI_API_KEY=YOUR_RESPAN_API_KEY

No separate provider key needed. The Respan gateway handles provider authentication.

3

Run Hermes

hermes

All LLM calls now route through Respan.

Switch models

Change model.default in ~/.hermes/config.yaml to use any of the 1000+ models available through the gateway.

model:
  default: gpt-4o
  # default: claude-sonnet-4-5-20250929
  # default: gemini-3.5-flash

See the full model list.