> For the complete documentation index, see [llms.txt](https://docs.cortecs.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.cortecs.ai/integration-examples/agents-and-automations/hermes-agent.md).

# Hermes Agent

[Hermes Agent](https://hermes-agent.nousresearch.com/) is an autonomous agent from Nous Research with persistent memory, tools, and messaging integrations. It supports custom OpenAI-compatible endpoints.

{% hint style="info" %}
Before you begin, create a Cortecs API key by following the [Quickstart](/quickstart.md) and choose a tool-calling model from the [model catalog](https://cortecs.ai/serverlessModels).
{% endhint %}

## 1. Install Hermes Agent

On macOS, Linux, or WSL:

```bash
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
```

See the [Hermes Agent documentation](https://hermes-agent.nousresearch.com/docs) for other platforms.

## 2. Connect to Cortecs

Run:

```bash
hermes model
```

Select **Custom endpoint**, then enter:

* **API base URL:** `https://api.cortecs.ai/v1`
* **API key:** Your Cortecs API key
* **Model name:** The exact Cortecs model ID
* **Context length (if prompted):** The catalog value; Hermes requires at least 64,000 tokens

Start the agent with:

```bash
hermes chat
```

For more configuration options, see the [Hermes Agent provider documentation](https://hermes-agent.nousresearch.com/docs/integrations/providers).