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.
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.
Stars
7,681
Forks
565
Language
Python
License
Apache-2.0
Category
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.
Featured in
Recent Releases
Compare
Related agents
e2b-dev/E2B
Open-source, secure environment with real-world tools for enterprise-grade agents.
e2b-dev/infra
Infrastructure that's powering E2B Cloud.
always-further/nono
Secure, kernel-enforced sandbox CLI and SDKs for AI agents. Capability-based isolation with...
boxlite-ai/boxlite
Sandboxes for every agent. Embeddable, stateful, snapshots, and hardware isolation.
zerobootdev/zeroboot
Sub-millisecond VM sandboxes for AI agents via copy-on-write forking