Ask HN: Why are so many rolling out their own AI/LLM agent sandboxing solution?

21 points by ATechGuy | 9 comments
Seeing a lot of people running coding agents (Claude Code, etc.) in custom sandboxes Docker/VMs, firejail/bubblewrap, scripts that gate file or network access.

Curious to know what's missing that makes people DIY this? And what would a "good enough" standard look like?

Loading...
Loading...
Loading...
Loading...