"You [...] describ[e] what your agent is and isn't allowed to do. #IronCurtain compiles this into a deterministic security policy [...], validates the compiled rules against generated test scenarios, and then enforces the policy at runtime on every tool call. [...]."

GitHub - provos/ironcurtain: A secure* runtime for autonomous AI agents. Policy from plain-English constitutions. (*https://ironcurtain.dev)

A secure* runtime for autonomous AI agents. Policy from plain-English constitutions. (*https://ironcurtain.dev) - provos/ironcurtain

GitHub (github.com)