OpenSandbox and python-sandbox
About OpenSandbox
alibaba/OpenSandbox
OpenSandbox is a general-purpose sandbox platform for AI applications, offering multi-language SDKs, unified sandbox APIs, and Docker/Kubernetes runtimes for scenarios like Coding Agents, GUI Agents, Agent Evaluation, AI Code Execution, and RL Training.
This platform allows AI developers to safely test and run their AI applications, like coding agents or those that automate web browsers, in isolated environments. You input your AI code or agent, and it provides a secure, controlled space for execution and evaluation without affecting your main systems. It's designed for AI engineers and researchers who build and deploy intelligent agents and applications.
About python-sandbox
onyx-dot-app/python-sandbox
Secure and lightweight Python code execution environment for LLMs
This project provides a secure way for AI applications to run Python code. It takes Python code and any necessary files, executes them in a safe, isolated environment with strict resource limits, and returns the output (like print statements or results) and any generated files. This is designed for AI developers building agentic applications, large language model (LLM) tools, or any system that needs to execute untrusted code safely.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work