Commit

db93771

Some thoughts raised in my mind this morning, let me tell you. We embed AI models in our applications and give them tools to call. Being careful with these tool is what makes the AI kind of sandboxed. But now, models are smart enough to search for vulns, they may try to run…

Younes @younes-io2d762afe1

run the agents in a sandbox with kernel-level control : https://github.com/nolabs-ai/nono

GitHubGitHub - nolabs-ai/nono: agent runtime security - zero trust, zero setup, zero latency agent sandboxingagent runtime security - zero trust, zero setup, zero latency agent sandboxing - nolabs-ai/nono

Nehal Hasnayeen @Hasnayeen2d7cc2db6

are you using this? how does this compare to using bubblewrap?

Younes @younes-io2d0d928d4

not yet but saw it on a demo from the company's founder at oss europe. i have never heard of bubblewrap

Nehal Hasnayeen @Hasnayeen1d

https://github.com/containers/bubblewrap zed use this for their agent sandboxing

GitHubGitHub - containers/bubblewrap: Low-level unprivileged sandboxing tool used by Flatpak and similar projectsLow-level unprivileged sandboxing tool used by Flatpak and similar projects - containers/bubblewrap

15:51 · Oct 27, 2026commit db93771