Kimi CLI

Configuration

Install Kimi CLI and Node.js 20 or later. Create an AudioLab workspace key with llm.write, available credits, and access to the selected model. Export it as AUDIOLAB_API_KEY in the terminal that launches the agent.

# Generated by AudioLab Router. Credentials are read from your environment.
export OPENAI_BASE_URL='https://api.tryaudiolab.ai/v1'
export OPENAI_API_KEY="$AUDIOLAB_API_KEY"

[providers.audiolab]
type = "openai_legacy"
base_url = "https://api.tryaudiolab.ai/v1"
api_key = ""

[models.audiolab]
provider = "audiolab"
model = "openai/gpt-6-astra"
max_context_size = 128000

Automatic Setup

The command previews the files and fields it changes. Confirm to apply; it stores a private backup and prints an undo command. It does not store the API key or change your shell profile. Automatic file setup supports macOS and Linux.

npx https://tryaudiolab.ai/cli/router-0.1.0.tgz setup --agent kimi

Launch

npx https://tryaudiolab.ai/cli/router-0.1.0.tgz run kimi

Verify the Connection

Send a short text prompt, then a read-only tool request in a disposable project. Check the model, request record, and usage in Router. Test streaming and a follow-up turn before using a longer workflow. Client-specific tools and permissions remain managed by Kimi CLI.

The setup command can check authentication and model discovery without generating a response. See the protocol contracts for model and feature limits.

Reference

Kimi CLI Configuration — Official Documentation

AudioLab Setup Command