Kilo Code

Connect Kilo Code to APIClaw through an OpenAI Compatible custom provider.

Kilo Code supports custom OpenAI-compatible endpoints. Point it at APIClaw to use your plan's models from the VS Code extension or Kilo CLI.

Watch the setup walkthrough:

Prerequisites

1. Install Kilo Code (VS Code extension) or Kilo CLI.
2. Create an API key in the API Keys dashboard.
3. Copy a full model ID from the model hub.

VS Code extension

1. Open Settings (gear icon) and go to the Providers tab.
2. Scroll to the bottom and click Custom provider.
3. Paste this Base URL:

https://apiclaw.biz/v1

1. Fill in the dialog:

1. Click Submit. Select an APIClaw model in the model picker.

OpenAI Compatible is the straightforward choice. APIClaw also serves the Responses API at https://apiclaw.biz/v1/responses, so OpenAI Responses works too if your build prefers it.

Kilo CLI / config file

npm install -g @kilocode/cli
export APICLAW_API_KEY="sk-your-apiclaw-key"

The provider block belongs in the global ~/.config/kilo/kilo.jsonc. Kilo resolves {env:...} only in the global config, so the same block in a project file silently fails to authenticate:

{
  "$schema": "https://app.kilo.ai/config.json",
  "model": "openai-compatible/YOUR_MODEL_ID",
  "provider": {
    "openai-compatible": {
      "options": {
        "baseURL": "https://apiclaw.biz/v1",
        "apiKey": "{env:APICLAW_API_KEY}"
      },
      "models": {
        "YOUR_MODEL_ID": {
          "name": "YOUR_MODEL_ID",
          "tool_call": true,
          "limit": { "context": 200000, "output": 16384 }
        }
      }
    }
  }
}

Replace YOUR_MODEL_ID with the exact ID from the model hub, and set limit to the model's real context and output sizes. A custom model with no limit resolves to zero, which switches off conversation compaction and lets history grow until the request is rejected.

Inside the CLI you can also run /connect to enter the credentials interactively, and kilo models to confirm the provider is active.

Verify

Open a project and send a simple coding task. A normal model response means the connection is complete. Confirm the request in logs.

Troubleshooting

• Invalid API key: re-paste the key with no extra spaces; confirm it is active in API Keys.
• Model not found: use the full model ID from the model hub, not a short alias.
• Connection errors: Base URL must be exactly https://apiclaw.biz/v1 (include /v1, do not append /chat/completions unless your Kilo build requires a full endpoint URL).