Skip to content

Add brood-box to Frameworks for LLM security#305

Open
JAORMX wants to merge 1 commit intotensorchord:mainfrom
JAORMX:add-brood-box
Open

Add brood-box to Frameworks for LLM security#305
JAORMX wants to merge 1 commit intotensorchord:mainfrom
JAORMX:add-brood-box

Conversation

@JAORMX
Copy link
Copy Markdown

@JAORMX JAORMX commented Mar 20, 2026

Adds brood-box to the Frameworks for LLM security table.

brood-box is an open-source CLI tool (Apache-2.0) that runs AI coding agents (Claude Code, Codex, OpenCode) inside hardware-isolated microVMs. It mitigates the security risks of LLM-powered agents by providing:

  • Hardware isolation — KVM microVMs via libkrun, not just containers
  • Snapshot isolation — COW workspace snapshots with interactive per-file review before changes flush back
  • Egress control — DNS-aware network policies restrict what the agent can reach
  • MCP authorization — Cedar-based profiles to restrict agent MCP operations

Entry placed alphabetically before Plexiglass, matching the existing table format with GitHub star badge.


🤖 Generated with Claude Code and Brood Box

@JAORMX
Copy link
Copy Markdown
Author

JAORMX commented Mar 20, 2026

Oops, I'll fix this and sign the commit

Signed-off-by: Juan Antonio Osorio <ozz@stacklok.com>
@JAORMX
Copy link
Copy Markdown
Author

JAORMX commented Mar 25, 2026

fixed

nicoloboschi pushed a commit to nicoloboschi/Awesome-LLMOps that referenced this pull request Mar 30, 2026
…rm category (tensorchord#305)

Co-authored-by: samzong <samzong@users.noreply.github.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant