Nanobot

Install and check Nanobot

Recommended with uv:

uv tool install nanobot-ai

Or with pipx:

pipx install nanobot-ai

Verify:

nanobot --version

Set the API Key env var

Nanobot's OpenAI-compatible provider reads OPENAI_API_KEY. If you also use other OpenAI services locally, set it only in the terminal session where you start Nanobot.

export OPENAI_API_KEY="sk-yolo-..."

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

set OPENAI_API_KEY=sk-yolo-...

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

Edit config.json

Nanobot's default config file is:

~/.nanobot/config.json

On Windows this is usually:

%USERPROFILE%\.nanobot\config.json

Add or merge the following config:

{
  "agents": {
    "defaults": {
      "model": "deepseek-v4-pro",
      "provider": "deepseek"
    }
  },
  "providers": {
    "deepseek": {
      "apiKey": "${OPENAI_API_KEY}",
      "apiBase": "https://api.yolorouter.com/v1"
    }
  }
}

Field notes:

• agents.defaults.provider: use a provider that Nanobot already supports. The example uses deepseek; if you use another supported provider, change this value and the matching entry under providers.
• providers.deepseek.apiKey: reads your Yolo Router API Key from OPENAI_API_KEY
• providers.deepseek.apiBase: your Yolo Router OpenAI-compatible endpoint, with /v1
• agents.defaults.model: must exactly match the model ID in the Yolo Router console

In short, "provider": "deepseek" means Nanobot should use its supported DeepSeek provider adapter, while apiKey and apiBase redirect that adapter to your Yolo Router Key and URL.

Start Nanobot

Open your project directory and run:

nanobot agent

If you need to select a model, open Nanobot's model selector and choose the model under the provider you configured.

Test the connection

Send:

Introduce the model you are using in one sentence.

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