> ## Documentation Index
> Fetch the complete documentation index at: https://docs.muna.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Hermes

> Use open models on Muna in Hermes Agent.

[Hermes Agent](https://hermes-agent.nousresearch.com) connects to OpenAI-compatible APIs as a custom endpoint.

## Configuring Hermes

Run the setup wizard and choose **Custom endpoint**:

```bash theme={null}
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`:

```yaml theme={null}
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`:

```text theme={null}
/model custom:@google/gemma-4-26b-a4b-it
```

See [Models](/inference/models) for every model you can use.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.