agent.shield

agent.shield is a security firewall for AI agents. It sits in front of your systems as a transparent HTTP proxy: every request your agent makes runs through it, gets matched against your policies — plain regex on method, path, and body — and safe traffic is forwarded the instant it arrives. Nothing slows down until something dangerous shows up.

When a request looks destructive — a DELETE, a drop table, an rm -rf, a kubectl delete — agent.shield holds it in an approval queue and waits for a human to approve or deny, then forwards or blocks accordingly. Every decision, held or passed, lands in an audit log you can read later. Point your agent at one url and you have a human in the loop for anything that can't be undone.