# Connect Hermes Agent

https://omnimodel.me/apps/hermes-agent

> Nous Research's open-source terminal agent that codes, runs commands, and remembers your preferences.

## Use cases

For a long-lived terminal agent that writes code, runs commands, and builds up memory and skills across sessions. Set the custom endpoint with Custom endpoint in `hermes model`; it is saved to `~/.hermes/config.yaml`.

## Tips

A coding agent sends many long requests per task, so pick a long-context model with tool calling and set a daily spend limit on the key.

## Reasoning effort

Whether a reasoning level is sent depends on the reasoning setting you give the model (`reasoning_effort` on the Chat API). The platform follows the levels the serving line accepts: a level the upstream rejects becomes the next higher accepted level, or its highest one. If the model cannot turn reasoning off, asking for it returns 422 `model.reasoning_off_unsupported`. Each model's table is under Reasoning effort on its page in the [catalog](/catalog?lang=en); rewritten calls show the rewrite in usage records.

## If it cannot connect

1. Use `https://omnimodel.me/v1` as the API host, without `/chat/completions`.
2. The key starts with `key_` and is not paused or revoked; `auth.invalid_key` means the key cannot be used.
3. The model ID matches the [catalog](/catalog) and is in the key's allowed models.
4. `billing.insufficient_credit` means the balance is too low; see [common errors](/docs/errors?lang=en) for more.

## Setup

1. Install: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash.
2. Run hermes model, pick Custom endpoint, and enter the API host, key, and model ID below; or write the block below into ~/.hermes/config.yaml directly.
3. Run hermes to start a session.

## Settings

- API host：`https://omnimodel.me/v1`
- API key：`YOUR_API_KEY`
- Model：`MODEL_ID`

> This setup follows the Hermes Agent docs and has not been tested by the platform yet; if something breaks, open a ticket with the request ID.

```yaml
model:
  provider: custom
  base_url: https://omnimodel.me/v1
  api_key: YOUR_API_KEY
  default: MODEL_ID
```

## FAQ

### It says the context window is too small at startup.

Hermes Agent needs at least 64K of context. Pick a longer-context model; if the model is long enough but not detected, add context_length under model in config.yaml.

### Does setting OPENAI_BASE_URL help?

No. Custom endpoints only read base_url from hermes model or config.yaml.