ipybox

ipybox is a lightweight and secure Python code execution sandbox based on IPython and Docker. You can run it locally on your computer or remotely in an environment of your choice - no API key required.

Designed for AI agents that interact with their environment through code execution, like freeact agents, it is also well-suited for many other secure code execution use cases. ipybox is fully open-source and distributed under the Apache 2.0 license.

Features

• Secure code execution inside Docker containers
• Stateful code execution with IPython kernels
• Stream code execution output as it is generated
• Install Python packages at build time or runtime
• Return plots generated with visualization libraries
• Invocation of MCP servers via generated client code
• Flexible deployment options, local or remote
• asyncio API for managing the execution environment

Documentation

• User Guide
• API Docs

Quickstart

Install ipybox Python package:

pip install ipybox

Execute Python code in an ipybox container:

import asyncio
from ipybox import ExecutionClient, ExecutionContainer

async def main():
    async with ExecutionContainer(tag="ghcr.io/gradion-ai/ipybox:minimal") as container:
        async with ExecutionClient(port=container.executor_port) as client:
            result = await client.execute("print('Hello, world!')")
            print(f"Output: {result.text}")

if __name__ == "__main__":
    asyncio.run(main())