nanobot

nanobot is a lightweight terminal agent that configures providers and model presets in JSON. It can call ModelGo through its OpenAI-compatible API.

Prerequisites

Python 3.11+ is installed.
A ModelGo API key is available from ModelGo Console.
You know the logical model ID from the Model Catalog.

1. Install nanobot

bash

python -m pip install nanobot-ai
nanobot onboard --wizard

The default config is ~/.nanobot/config.json.

2. Configure a ModelGo provider

Merge these fields into ~/.nanobot/config.json:

json

{
  "providers": {"modelgo": {
    "apiKey": "${MODELGO_API_KEY}",
    "apiBase": "https://api.modelgo.ai/v1"
  }},
  "modelPresets": {"ModelGo": {
    "provider": "modelgo",
    "model": "your-model-id",
    "maxTokens": 4096,
    "contextWindowTokens": 65536,
    "temperature": 0.1
  }},
  "agents": {"defaults": {"modelPreset": "ModelGo"}}
}

bash

export MODELGO_API_KEY="sk-your-token"

Leave apiType unset for a custom OpenAI-compatible endpoint.

3. Verify the connection

bash

curl https://api.modelgo.ai/v1/models -H "Authorization: Bearer $MODELGO_API_KEY"
nanobot agent -m "Describe this project in one sentence"

Troubleshooting

nanobot cannot find the model

Make sure modelPresets.ModelGo.provider matches providers.modelgo and that the JSON is valid.

401 or endpoint errors

Confirm the key is exported and apiBase is exactly https://api.modelgo.ai/v1.

Related docs

First API Call: Create a key, list models, and verify ModelGo.
nanobot OpenAI-compatible provider guide: Review the JSON configuration.
Authentication: Learn safe API key handling.