We Built Secure, Scalable Agent Sandbox Infrastructure

Re:We Built Secure, Scalable Agent Sandbox Infrastructure by yakkomajuri on Friday February 27, 2026 @03:01PM (#47184824)

I think this is pretty standard and similar to approaches that are evolving naturally (I've certainly used very similar patterns).

I'd be pretty keen to actually hear more about the Unikraft setup and other deeper details about the agent sandboxes regarding the tradeoffs and optimizations made. All the components are there but has someone open-sourced a more plug-and-play setup like this?

[ Parent | on HN ]

Re:We Built Secure, Scalable Agent Sandbox Infrastructure by LarsenCC on Friday February 27, 2026 @09:58PM (#47189643)

Agreed, the pattern is converging across the industry. The Unikraft setup is where it gets interesting for us with sub-second boots (or sub 100ms even), scale-to-zero that suspends the VM after a few seconds of idle (frees resources), and dedicated bare metal in AWS so we're not sharing hardware.

We haven't open-sourced the control plane glue yet but it's something we're thinking about. browser-use itself is open source. The sandbox infra on top is the proprietary part for now.

[ Parent | on HN ]

Re:We Built Secure, Scalable Agent Sandbox Infrastructure by yakkomajuri on Saturday February 28, 2026 @02:42PM (#47199348)

Exactly, this is the very stuff I'd be interested to hear more about. Great work on all this btw and best of luck going forward!

[ Parent | on HN ]

Re:We Built Secure, Scalable Agent Sandbox Infrastructure by nicklo on Saturday February 28, 2026 @12:56PM (#47198252)

I’m building a self-hostable, open source agent sandbox orchestrator here: https://github.com/ash-ai-org/ash-ai

[ Parent | on HN ]

Re:We Built Secure, Scalable Agent Sandbox Infrastructure by pavitrabhalla on Tuesday March 03, 2026 @06:44PM (#47240815)

We are building a plug-and-play setup for this at superserve.ai

[ Parent | on HN ]