Docker Sandboxes – Disposable, isolated sandboxes for AI agents

Here's another sandbox that I found interesting: https://github.com/ashishb/amazing-sandbox

So it's basically a container with a fancy name, innit?

TO me, that's the important distinction: sandboxing limits what the agent can do but it doesn't necessarily enforce that the agent must run inside the sandbox. You need a separate control layer to enforce that boundary.

Just a small meta note: most of the comments in this thread appear to be posting their own codebase (typically AI-generated) that accomplishes the same goal. It's interesting that this problem is simultaneously in high demand and yet considered trivial enough to vibe code per-user solutions to it.

On Linux, you can skip Docker and use bubblewrap. Some inspiration: https://blog.gpkb.org/posts/ai-agent-sandbox/

...or...just hear me out now...we could limit it in the harness.

Don't give it shell access, just predefined tools.

The linked page implies there is no linux support, I wonder why. It's there in the docs if you hunt for it.

Docker management will fail their tech at every opportunity.

[dead]

[flagged]

[dead]

[dead]

[flagged]

[dead]

[dead]

[dead]

[dead]