Moonshot AI

Use Moonshot AI (Kimi) models with Docker Agent.

Overview

Moonshot AI serves its Kimi model family through an OpenAI-compatible API. The Kimi K2 models have strong momentum for coding and agentic tasks. Docker Agent includes built-in support for Moonshot AI as an alias provider.

Setup

1. Create an API key from the Moonshot AI console.

2. Set the environment variable:

   export MOONSHOT_API_KEY=your-api-key
   

Usage

Inline Syntax

The simplest way to use Moonshot AI:

agents:
  root:
    model: moonshot/kimi-k2-0905-preview
    description: Assistant using Moonshot AI
    instruction: You are a helpful assistant.

Named Model

For more control over parameters:

models:
  moonshot_model:
    provider: moonshot
    model: kimi-k2-0905-preview
    temperature: 0.7
    max_tokens: 8192

agents:
  root:
    model: moonshot_model
    description: Assistant using Moonshot AI
    instruction: You are a helpful assistant.

Available Models

Moonshot AI exposes a vendor-controlled Kimi model lineup. Check the Moonshot API documentation for current model IDs, context limits, and pricing.

Model IDs are case-sensitive and must be passed exactly as the catalogue lists them.

How It Works

Moonshot AI is implemented as a built-in alias in Docker Agent:

• API Type: OpenAI-compatible (openai_chatcompletions)
• Base URL: https://api.moonshot.ai/v1
• Token Variable: MOONSHOT_API_KEY

Example: Code Assistant

agents:
  coder:
    model: moonshot/kimi-k2-0905-preview
    description: Code assistant using Kimi K2
    instruction: |
      You are an expert programmer.
      Write clean, well-documented code and follow language best practices.
    toolsets:
      - type: filesystem
      - type: shell
      - type: think