Source: https://ailoot.ai/docs/integrations/hermes-agent/
Canonical: https://ailoot.ai/docs/en/integrations/hermes-agent/
Language: en

[Terminal agents](https://ailoot.ai/docs/en/integrations/#agents) 

# Hermes Agent

[Markdown](https://ailoot.ai/docs/en/integrations/hermes-agent/index.md)

Terminal agent · OpenAI Chat, OpenAI Responses, Anthropic Messages

| Format | Where to set it up |
| --- | --- |
| OpenAI Chat, OpenAI Responses, Anthropic Messages | hermes model → “Custom endpoint (self-hosted / VLLM / etc.)” or ~/.hermes/config.yaml (the model section or providers dictionary) |

## [](https://ailoot.ai/docs/integrations/hermes-agent/#setup)Setup

Copy the configuration and replace `sk-...` with your key from the Ailoot Dashboard. Prefer storing the key in the environment variable `AILOOT_API_KEY`, if the application supports it.

Before starting, request GET /v1/models with your Ailoot key. Choose an exact model ID whose methods include POST /v1/chat/completions, POST /v1/responses, POST /v1/messages, then use that ID in the configuration. For agents, also check tool support and the features required by your client version.

`~/.hermes/config.yaml`

```yaml
model:
  default: claude-sonnet-5-5
  provider: custom
  base_url: https://api.ailoot.ai/v1
  key_env: AILOOT_API_KEY

# multiple formats at once: named providers:
providers:
  ailoot:
    api: https://api.ailoot.ai/v1
    key_env: AILOOT_API_KEY
    transport: chat_completions
    default_model: gpt-6.1-sol
  ailoot-claude:
    api: https://api.ailoot.ai
    key_env: AILOOT_API_KEY
    transport: anthropic_messages
    default_model: claude-sonnet-5-5

# in the session: /model custom:claude-sonnet-5-5
```

This configuration reads the key from the environment variable `AILOOT_API_KEY`. Set it before starting the application:

```bash
export AILOOT_API_KEY="sk-..."   # add to ~/.zshrc or ~/.bashrc
```

```powershell
setx AILOOT_API_KEY "sk-..."   # then restart the terminal
```

Example model: `claude-sonnet-5-5`. Choose any other model from the [catalog](https://ailoot.ai/models/en/) — check that it supports the format you need.

## [](https://ailoot.ai/docs/integrations/hermes-agent/#notes)Good to know

transport: chat\_completions (OpenAI Chat), anthropic\_messages (Anthropic Messages), or codex\_responses (OpenAI Responses). LLM\_MODEL in .env is no longer used; OPENAI\_BASE\_URL applies only to the openai-api provider. For anthropic\_messages, use a URL without /v1; the Anthropic SDK appends /v1/messages. Auxiliary tasks (image recognition, history compaction) use the same main model by default.

## [](https://ailoot.ai/docs/integrations/hermes-agent/#check)Test

- For the OpenAI format, the URL is `https://api.ailoot.ai/v1` (or the full path if the application asks for a full URL).
- For the Anthropic format, the URL is `https://api.ailoot.ai` without `/v1`.
- Ask a short question. If you get an error, check the code and Request ID, then consult [Errors and limits](https://ailoot.ai/docs/en/errors/).
- 404 immediately after setup almost always means the URL is wrong: an extra or missing `/v1`.
- 402 — insufficient balance for the reserve. Agents reserve more than chat: [why](https://ailoot.ai/docs/en/billing/reserve/).

Application documentation: [https://hermes-agent.nousresearch.com/docs/integrations/providers](https://hermes-agent.nousresearch.com/docs/integrations/providers)

Still have questions? Send your Request ID and a description — we'll help you troubleshoot.[Contact support](mailto:support@ailoot.ai)

## Ailoot · The company and its project portfolio





Ailoot combines established operating experience, a large client base, stable service and ongoing KPI control.





The company and its project portfolio: millions of customers; monthly sales in the billions.





Ailoot brings that operating experience to API access for AI features in customer products, agents, applications and automations.