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.

74
/ 100
Verified

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.

7,681 stars. Used by 1 other package. Actively maintained with 326 commits in the last 30 days. Available on PyPI.

Use this if you need a secure, isolated, and scalable environment to develop, test, and evaluate AI agents and applications, especially those that execute code or interact with systems like web browsers.

Not ideal if you are looking for a simple, off-the-shelf AI model or a tool for basic data analysis without agentic capabilities.

AI development agent evaluation secure execution AI testing RL training
Maintenance 22 / 25
Adoption 11 / 25
Maturity 22 / 25
Community 19 / 25

How are scores calculated?

Stars

7,681

Forks

565

Language

Python

License

Apache-2.0

Last pushed

Mar 13, 2026

Commits (30d)

326

Dependencies

4

Reverse dependents

1

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/alibaba/OpenSandbox"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.