Comment by arjunchint
1 month ago
Haha we made a demo couple of months back with the same underlying premise of "The Browser Sandbox is All You Need": https://www.youtube.com/watch?v=PrSYYaZCxsc
We essentially leveraged sandboxes built into Chromium browsers for LLM generated code execution.
This actually simplifies a lot of the setup in the blog post, as it leverages existing sandboxing infra exposed for extensions: https://developer.chrome.com/docs/extensions/how-to/security...
The browser sandbox is incredible for isolated code execution, but I've found it tricky for "local agent" workflows where you actually want the LLM to use the host CLI or filesystem, just safely.
I built a process supervisor (Vallignus) for that specific "OS-level" use case. It wraps the agent to enforce egress filtering and loop detection so it can use local tools without running wild.
Code is here if you're curious: https://github.com/jacobgadek/vallignus