Hermes

Hermes Agent connects to OpenAI-compatible APIs as a custom endpoint.

Configuring Hermes

Run the setup wizard and choose Custom endpoint:

hermes model

Enter https://inference.muna.ai/v1 as the base URL, your Muna API key, and a model tag like @qwen/qwen-3.8-27b. Or set it directly in ~/.hermes/config.yaml:

model:
  default: "@qwen/qwen-3.8-27b"
  provider: custom
  base_url: https://inference.muna.ai/v1
  key_env: MUNA_API_KEY

key_env reads the key from your environment, so it never lands in the config file.

Switching Models

Switch to another Muna model mid-session with /model:

/model custom:@google/gemma-4-26b-a4b-it

See Models for every model you can use.

Get Started

Coding Agents

Local Inference

Configuring Hermes

Switching Models

​Configuring Hermes

​Switching Models

Configuring Hermes

Switching Models