Kimi CLI Example

Run Kimi Code CLI (Moonshot AI) inside an OpenSandbox container.

Start OpenSandbox server [local]

Pre-pull the code-interpreter image (includes Python 3.12+):

docker pull sandbox-registry.cn-zhangjiakou.cr.aliyuncs.com/opensandbox/code-interpreter:v1.1.0

# use docker hub
# docker pull opensandbox/code-interpreter:v1.1.0

Then start the local OpenSandbox server, stdout logs will be visible in the terminal:

uv pip install opensandbox-server
opensandbox-server init-config ~/.sandbox.toml --example docker
opensandbox-server

Create and Access the Kimi Sandbox

# Install OpenSandbox package
uv pip install opensandbox

# Run the example (requires SANDBOX_DOMAIN / SANDBOX_API_KEY / KIMI_API_KEY)
uv run python examples/kimi-cli/main.py

The script installs Kimi Code CLI (pip install kimi-cli) at runtime (Python 3.12+ is already in the code-interpreter image), then sends a simple request kimi -p "Compute 1+1=?.". Auth is passed via KIMI_API_KEY, and you can override endpoint/model with KIMI_BASE_URL / KIMI_MODEL_NAME.

Environment Variables

Variable	Default	Description
SANDBOX_DOMAIN	localhost:8080	Sandbox service address
SANDBOX_API_KEY	(optional for local)	API key if your server requires authentication
SANDBOX_IMAGE	sandbox-registry.cn-zhangjiakou.cr.aliyuncs.com/opensandbox/code-interpreter:v1.1.0	Sandbox image to use
KIMI_API_KEY	(required)	Your Moonshot AI / Kimi API key
KIMI_BASE_URL	(optional)	Kimi API endpoint (defaults to Kimi's official endpoint)
KIMI_MODEL_NAME	kimi-k2.5	Model to use

References

• Kimi Code CLI - Official Kimi Code CLI repository
• Moonshot AI Platform - API key management and documentation
• Kimi CLI Documentation - Full CLI documentation
• Source code on GitHub