Take a look at https://github.com/Tako-Research/TakoVM!
Ask HN: Secure wrapper for coding agents?
11–20 of 26 posts
Re: Ask HN: Secure wrapper for coding agents?
#12agent-pd was posted as a Show HN fairly recently, might be what you are remembering? https://github.com/varmabudharaju/agent-pd/
Re: Ask HN: Secure wrapper for coding agents?
#13[flagged]
Re: Ask HN: Secure wrapper for coding agents?
#14[dead]
Re: Ask HN: Secure wrapper for coding agents?
#15This may be too naive, but I created a user on my linux box who doesn't have very many permissions. Then I sudo to that user, use firejail to start pi in a dev project directory, and let it have at it.
My projects are usually very limited with respect to external dependencies and that is part of prompts or markdown files describing various project goals, plans, and current state.
My operating theory is that this probably won't get my systems borked. I wasn't patient enough to dig deeper.
Re: Ask HN: Secure wrapper for coding agents?
#16[dead]
Re: Ask HN: Secure wrapper for coding agents?
#17I build a local, cross platform virtual machine for this purpose: https://github.com/smol-machines/smolvm
Re: Ask HN: Secure wrapper for coding agents?
#18I believe you're looking for Era. It uses libkrun for local microVM isolation and was built specifically to solve the "LLM hallucinated a destructive bash command" problem without the overhead of a massive VM. Another one that handles this gracefully is Yolobox, which uses rootless Podman. Both are actively maintained and cut through the noise of the thousands of generic wrapper repos out there right now.
Era links to https://github.com/smol-machines/smolvm now
Yep, I needed to go deeper down the stack in order to get to the lightweight optimizations I needed.
Re: Ask HN: Secure wrapper for coding agents?
#19[flagged]
Re: Ask HN: Secure wrapper for coding agents?
#20[flagged]