Open
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
We've been building brood-box, a CLI that runs AI coding agents (Claude Code, Codex, OpenCode) inside hardware-isolated microVMs.
The idea is simple: your agent gets a full Linux environment to work in, but it's running inside a KVM microVM. So even if a prompt injection convinces it to
cat ~/.ssh/id_rsaorcurlyour secrets somewhere... there's nothing to find, and nowhere to send it.It also does COW snapshot isolation (diff and review every change before it touches your real workspace), DNS-aware egress control, and Cedar-based MCP authorization profiles.
Fits nicely in the Agent infrastructure section alongside the other sandboxing tools.
🤖 Generated with Claude Code and Brood Box