Hermes Agent

iBefore you start

Hermes Agent is installed and available as hermes.
A working Yolo Router endpoint, for example https://api.yolorouter.com.
A Yolo Router API Key generated from the console.
The model ID you want to use, for example deepseek-v4-pro. It must exactly match the model ID in the Yolo Router console.

Hermes Agent supports Custom endpoint and config-file based third-party model setup. For Yolo Router, point base_url to the OpenAI-compatible /v1 endpoint and keep model IDs aligned with the console.

Setup

Check Hermes Agent

Run:

hermes --version

If it is not installed yet, install Hermes Agent using the official installation flow before continuing.

Set the Yolo Router API Key

The examples below use YOLOROUTER_API_KEY; the config file will read this variable.

export YOLOROUTER_API_KEY="sk-yolo-..."

$env:YOLOROUTER_API_KEY = "sk-yolo-..."

set YOLOROUTER_API_KEY=sk-yolo-...

Do not write the real API Key into config files or commit it to your repository.

Edit the config file

Hermes Agent's default config file is usually:

~/.hermes/config.yaml

On Windows this is usually:

%USERPROFILE%\.hermes\config.yaml

Add or merge the following configuration:

provider:
  name: yolorouter
  type: openai_compat
  base_url: https://api.yolorouter.com/v1
  api_key: YOLOROUTER_API_KEY

models:
  - id: deepseek-v4-pro
    name: deepseek-v4-pro
    provider: yolorouter
    context_window: 128000
    max_output_tokens: 8192
    supports_reasoning: true
  - id: deepseek-v4-flash
    name: deepseek-v4-flash
    provider: yolorouter
    context_window: 128000
    max_output_tokens: 8192
    supports_reasoning: false

default_model: yolorouter/deepseek-v4-pro

Field notes:

type: use openai_compat for an OpenAI-compatible gateway
base_url: your Yolo Router OpenAI-compatible endpoint, with /v1
api_key: the environment variable name YOLOROUTER_API_KEY
models[].id: must exactly match the model ID in the Yolo Router console
default_model: the default model in <provider>/<model> format, for example yolorouter/deepseek-v4-pro

Use the Custom endpoint flow

If you prefer configuring through the TUI, run:

hermes model

Choose Custom endpoint, then enter:

Field	Value
Base URL	`https://api.yolorouter.com/v1`
API Key	`YOLOROUTER_API_KEY`
Model	`deepseek-v4-pro`

Save and reselect the model.

Test the connection

Send:

Introduce the model you are using in one sentence.

If Hermes Agent returns a normal response, the integration is working. You can also check the Yolo Router console for the corresponding request log.

Troubleshooting

provider or Custom endpoint does not appear

Confirm that your Hermes Agent version supports custom endpoints. Restart Hermes Agent after changing config.

401 Unauthorized

Make sure YOLOROUTER_API_KEY is set in the current shell and has no extra spaces.

404 or endpoint not found

Check that base_url is https://api.yolorouter.com/v1; do not use only the root endpoint.

Model not found

Confirm that models[].id exactly matches the model ID in the Yolo Router console.

Config changes do not take effect

Hermes Agent usually caches the current session's model selection. Close the current session and restart after changing config.

On this page