
Constrain what AI agents can reach
CROA is an open, vendor-neutral architecture for governing what AI agents can actually execute. Instead of relying on the agent to respect constraints, CROA separates intelligence from authority and constrains execution against registered invariants before state change. The public Pilot makes the approach reproducible: run it, inspect the evidence, and try to break the claim.
CROA is an open-source architecture that governs AI agent execution by separating intelligence from authority and enforcing constraints based on registered invariants. It allows developers to run, inspect, and validate the system's claims through a public Pilot.
A source that found nothing is a measurement. A source that has not run is a gap. Neither means the launch lacks the thing.