Connecting Hermes
Difficulty ⌨️ Advanced | API format OpenAI compatible | base_url
https://byesu.com/v1
https://byesu.com/v1gpt-5.5Hermes is a self-evolving AI agent open-sourced by Nous Research. It is OpenAI-compatible out of the box, so all you need to do is point its model backend at byesu — an AI API gateway with OpenAI-compatible and Anthropic-native endpoints. One key covers Claude, GPT-5.6, Grok and Gemini, billed pay-as-you-go with no subscription.
Before you start
First go to Console → Tokens and create a token (it looks like sk-xxxx), then pick the right group for the token — the group determines which models you can call and how you're billed (see Choosing a group).
Step 1: Configure (choose one)
Option 1: Command wizard (the easiest)
hermes modelIn the list of providers, choose Custom OpenAI-compatible endpoint, then fill in:
- base URL:
https://byesu.com/v1 - API key: your
sk-xxxx - Model: a model name available on byesu (such as
gpt-5.5orclaude-opus-4-8)
Option 2: Edit the config file by hand
Edit the model: section of ~/.hermes/config.yaml:
model:
provider: "custom" # custom OpenAI-compatible endpoint
base_url: "https://byesu.com/v1"
default: "gpt-5.5" # change to a model name on byesu
api_key: "sk-xxxx" # or leave empty and put it in ~/.hermes/.envSafer: put the key in .env
If you would rather not write the key into the config file, put it in ~/.hermes/.env:
OPENAI_API_KEY=sk-xxxxStep 2: Run it and verify
Start Hermes:
hermesSend it a short message. If it replies normally, you're connected ✅
Stuck?
- 401 / invalid token → the key was entered incorrectly (details)
- Model does not exist → the
defaultmodel name must match the one in the Console (details) - No available channel → the model is not in your token's group (Choosing a group, details)
- For anything else, see Common errors & fixes
