AI Tool Setup

ModelGo supports common AI coding clients and Agents. After you create an API key, use the official configuration tool for one-click setup; clients not covered by that tool can be configured manually through a custom provider.

bash
npx @model-go/config -r global

Select one or more tools when prompted. To configure every supported tool in an automated workflow, use:

bash
npx @model-go/config -k sk-your-token -r global --only all

Supported AI tools

ToolOfficial config toolManual setup docs
Hermes AgentSupportedSetup guide
Claude CodeSupportedSetup guide
Kilo CodeNot supportedSetup guide
ClineNot supportedSetup guide
CodexSupportedSetup guide
OpenClawSupportedSetup guide
DeepSeek HarnessNot supportedSetup guide
ZCodeNot supportedSetup guide
CursorNot supportedSetup guide
OpenCodeSupportedSetup guide
CC SwitchSupportedSetup guide
Cherry StudioNot supportedSetup guide
CrushSupportedSetup guide
Factory DroidSupportedSetup guide
Copilot CLISupportedSetup guide
nanobotSupportedSetup guide
Oh My PiSupportedSetup guide
CodeBuddySupportedSetup guide
Kilo CLINot supportedSetup guide

Before you connect

  1. Create an API key in the console.
  2. Run the command above and select the clients or Agents you want to configure.
  3. Confirm the site, Base URL, and masked API key when prompted. The configuration tool verifies the connection automatically.

To manage your ModelGo account, models, calls, and Skills from the terminal, continue to CLI Tools.

Integration guide

Most tools only need the following information to connect to ModelGo:

  1. API address: Use https://api.modelgo.ai/v1 for OpenAI-compatible APIs, or https://api.modelgo.ai for Anthropic-compatible APIs.
  2. API key: The token created in ModelGo Console.
  3. Model name: The logical model ID selected from the Model Catalog.

See the setup guide for each tool above for the exact configuration steps.