# GuardRail.Space AGENTS.md

Architectural guidelines and contribution rules for GuardRail.Space MVP.

- Architecture overview
- Tech stack and interfaces
- Testing commands and CI hints
- Contribution and code style rules
- MVP scope for safety contracts, policy engine, guard module, and adapters

The goal is to provide a production-ready scaffold that can be progressively extended:
- DSL for SafetyContracts (JSON-like for MVP)
- Runtime policy engine to veto or adjust actions
- Shadow planner for risk-proof alternatives
- Offline-first logging and reconciliation
- CatOpt bridge adapters for cross-domain interoperability
- HIL-ready integration hooks (Gazebo/ROS)
- Governance, audit trails, and privacy controls

If you add features, update this document to reflect schema changes and testing commands.