← All projects
Running AI at scale

OpenSandbox

Gives AI agents safe, walled-off computers to run code, use files and browse, on your own servers.

What it does

When AI agents run code or use a browser, it's safer to keep them in a sandbox, an isolated environment where mistakes can't harm the main system. OpenSandbox provides those sandboxes on your own infrastructure.

Agents can run commands, manage files, write code and operate browsers or desktops inside them. It controls network access and can let agents use outside services without exposing real passwords.

It starts locally with Docker and scales up on Kubernetes, and works with several programming languages and with MCP.

Who it's for

Teams building AI agents that need to run code or use computers safely.

Can I use it without coding?

Developers only. Needs Docker and Python, and is used through programming libraries. New to this? Start here.

Can I run it?

Cost
FreeNothing to pay or sign up for.
Runs on
Server
Privacy
Runs on your own device: your data stays with you
API key
Not needed

Try it

Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?

Before you install

  • Only download from the official GitHub page. Copies with similar names exist for many popular projects.
  • License (Apache-2.0): Permissive: free to use, change and share, including for business.
  • More on staying safe