zlacker

[return to "Sandboxing AI Agents in Linux"]
1. jaunty+zA[view] [source] 2026-02-03 19:59:19
>>speckx+(OP)
Really well targeted!

I'd been thinking of using toolbox or devcontainers going forward, but having to craft containers with all my stuff sounds so painful, feels like it would become another full-time job to make containers

Bubblewrap & passing in a bunch of the current system sounds like a great compromise!

I do wonder what isolation something like systemd-run can offer, if that is enough.

Part #2 to me, I also want observability as to what the agent changed. That was one place where containers are such a clear & huge advantage! Having an overlay that contains the changes to the filesystem is so explicit. There's also works like agentfs, that offer a FUSE filesystem backed by Turso DB (sqlite compatible).

◧◩
2. eikenb+Yq1[view] [source] 2026-02-04 00:34:47
>>jaunty+zA
Bubblewrap supports overlayfs mounts [1]. Seems like you should be able to replicate that flow with it.

[1] https://github.com/containers/bubblewrap/issues/412

[go to top]