---
url: https://docs.freetheai.org/guides/hermes-agent.md
description: >-
  Run Nous Research's Hermes Agent on free models through FreeTheAI, with hermes
  model or config.yaml.
---

# Hermes Agent

Hermes Agent uses FreeTheAI as a custom endpoint, set up with hermes model or in `config.yaml`.

Category: [Coding tools](/guides/#coding-tools). Before you start, you need a FreeTheAI account, an API key, and today's [check-in](/getting-started/check-in).

## Settings

| Setting | Value |
| --- | --- |
| Provider | `Custom endpoint` |
| API base URL | `https://api.freetheai.org/v1` |
| Model name | `fta/zai/glm-5.3` |
| API key | Your FreeTheAI key (`ftai_...`, 53 characters) |

## Steps

### Run the setup wizard

In a terminal (outside a chat session) run hermes model, choose Custom endpoint, and enter the API base URL, your key, and the model name.

### Or edit config.yaml

The same setup in `~/.hermes/config.yaml`:

```yaml
model:
  default: fta/zai/glm-5.3
  provider: custom
  base_url: https://api.freetheai.org/v1
  key_env: FTAI_KEY
```

### Switch models later

Inside a session, run /model custom:`fta/kimi/k3` to switch to another FreeTheAI model.

## Tips

* Hermes needs a model with at least 64K context. All the recommended FreeTheAI models qualify.
* In the Hermes desktop app: open Settings (the gear), go to the Model tab, set Endpoint to Custom Endpoint, press Setup custom endpoint, keep it on Local, enter the API base URL and your key, and press Save. The model list loads by itself.

## Common questions

### Can I keep the key out of config.yaml?

Yes. Set key_env to an environment variable name, such as `FTAI_KEY`, and export your key there.

## More help

* [Every API error and its fix](/errors)
* [Limits and the daily reset](/concepts/limits)
* [Hermes Agent website](https://hermes-agent.nousresearch.com) and [source code](https://github.com/NousResearch/hermes-agent)

::: info How this guide was checked
Checked against Hermes Agent's provider docs (custom endpoint) on 2026-09-29.
:::