Kilo CLI

Kilo CLI is a terminal coding agent with custom OpenAI-compatible providers. Because ModelGo CLI automation is not available for Kilo CLI, use /connect or a kilo.jsonc file.

Prerequisites

Node.js 18+ is installed.
A ModelGo API key is available from ModelGo Console.
You know the logical model ID from the Model Catalog.

1. Install Kilo CLI

bash

npm install -g @kilocode/cli
kilo --version

Run kilo in a project; /connect opens the interactive provider setup.

2. Add a ModelGo provider

Create kilo.jsonc in the project root (or edit the global config):

jsonc

{
  "$schema": "https://app.kilo.ai/config.json",
  "model": "modelgo/your-model-id",
  "provider": {
    "modelgo": {
      "options": {
        "apiKey": "{env:MODELGO_API_KEY}",
        "baseURL": "https://api.modelgo.ai/v1"
      },
      "models": {
        "your-model-id": {
          "name": "ModelGo / your-model-id",
          "tool_call": true
        }
      }
    }
  }
}

bash

export MODELGO_API_KEY="sk-your-token"

Alternatively choose /connect → OpenAI Compatible and enter the same Base URL, key, and model ID.

3. Verify the configuration

bash

curl https://api.modelgo.ai/v1/models -H "Authorization: Bearer $MODELGO_API_KEY"
kilo

Select the ModelGo model and send a small read-only task.

Troubleshooting

The provider is missing

Check JSONC syntax, the provider ID, and the model path, then restart Kilo.

401 or 404 responses

Confirm MODELGO_API_KEY is exported and baseURL is exactly https://api.modelgo.ai/v1.

Related docs

First API Call: Create a key, list models, and verify ModelGo.
Kilo CLI documentation: Review installation, /connect, and CLI commands.
Kilo custom models: Review OpenAI Compatible provider fields.