Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Docker Sandboxes – Disposable, isolated sandboxes for AI agents

docker.com

Post reply on HN
Print view View original

61–70 of 426 posts

Re: Docker Sandboxes – Disposable, isolated sandboxes for AI agents

#61

Post by globular-toast »

reddozen wrote: post #18

If any AI company was doing serious engineering isolated containers would have been a prerequisite to using their tools.

Anyone serious about security will want to bring their own sandbox anyway, not trust these, often proprietary, agents. I've never run an agent outside a sandbox. My first bubblewrap script for `claude` is now over a year old. The tools are available and if you learn to use them you can run any program in a sandbox.

But, in any case, why put in effort doing something people don't expect or ask for? We can assume everyone running agents is either a) using their own sandbox, or b) doesn't care. I think we can guess which category most people fall into. You could maybe argue about responsibility, but I don't think you can argue about "serious engineering".

Re: Docker Sandboxes – Disposable, isolated sandboxes for AI agents

#62

Post by dizhn »

Grimburger wrote: post #37

> Each agent runs inside a dedicated microVM with your dev environment What's a "microVM" and what's the security model here compared to using real virtual machines with actual constraints on breakouts? Is it marketing fluff? Incus/LXD has had VM's for a long time now. incus launch images:ubuntu/26.04 my-ubuntu-vm --vm incus exec my-ubuntu-vm -- bash

That's a full VM. Microvms are much smaller and they start up very very fast. In miliseconds.

Re: Docker Sandboxes – Disposable, isolated sandboxes for AI agents

#64

Post by dizhn »

binsquare wrote: post #22
laserlight wrote: post #3

Requires login. Garbage.

I build a OSS lightweight, portable VM for those that don't want lock ins: https://github.com/smol-machines/smolvm

This looks like gvisor but is a vm like firecracker right? Any reason you did not want to use firecracker?

(I am testing this now as a backend for my pet project which currently supports firecracker and gvisor. No network.)

Re: Docker Sandboxes – Disposable, isolated sandboxes for AI agents

#65

Post by eloisius »

Hugsun wrote: post #59
Schlagbohrer wrote: post #52

Can someone more versed in Docker explain to me how this is different than building my own docker container from a Dockerfile for using Pi agent harness? That's what I do currently. I use Docker Desktop in windows as the backend for that.

Docker containers use Linux kernel features to create an isolated environment, running on the same machine as docker is. This creates a virtual machine, with its own kernel, and runs the container in there. This gives stronger isolation and security guarantees.

I have the same question as GP. Your answer helps a little but not really. I might be naive, but I was under the impression that malicious code escaping a docker image and running amok on my host system was not something I should be too worried about. Especially if I run docker in rootless mode. Is that wrong?

For clarity I’m actually using podman, not Docker.

Re: Docker Sandboxes – Disposable, isolated sandboxes for AI agents

#68

Post by ai_fry_ur_brain »

navigate8310 wrote: post #48

I just made my own devcontainer that I copy on any project and load whatever harness I want in that repo. Harnesss' config and auth are simply mounted from the host, so no setup required at all. https://github.com/iodize6399/ai-devcontainer/tree/main/.dev...

[dead]

Re: Docker Sandboxes – Disposable, isolated sandboxes for AI agents

#70

Post by angry_octet »

Schlagbohrer wrote: post #52

Can someone more versed in Docker explain to me how this is different than building my own docker container from a Dockerfile for using Pi agent harness? That's what I do currently. I use Docker Desktop in windows as the backend for that.

It's a VM.
Post reply on HN