About MAREF

Mission

MAREF makes multi-agent AI systems provably safe. Not "we hope it's safe." Not "our red team didn't find anything." Provably safe — using TLA+ formal verification, Lyapunov stability analysis, and cryptographic audit trails.

We believe that as agents become infrastructure — like databases, networks, and DNS — they need infrastructure-grade governance. Not a bolted-on security scanner. A constitutional layer that every agent, every tool call, every decision passes through.

Why governance-first?

Because the data is clear: 88% of organizations already had an AI agent security incident. 94% don't have a mature strategy. Companies spend 17x more on "AI-powered security" than on "securing AI itself."

The market is building agents faster than safety can keep up. MAREF closes that gap — not by slowing development, but by putting guardrails in place so teams can move fast without breaking things.

What makes MAREF different

• TLA+ formal verification — Not "we tested it." Every governance state transition is mathematically proven.
• 8-layer defense architecture — From prompt injection to rogue agent detection. Defense in depth isn't a feature; it's the architecture.
• Recursive self-evolution — The system gets provably safer over time. FNR -60% over 200 rounds, Lyapunov-proven convergence.
• Zero-trust identity per agent — Ed25519 signing for every decision. Every action is cryptographically attributable.
• National-grade cryptography — SM2/SM3/SM4-GCM for compliance with Chinese regulations (GB/T 32918, etc.).

Project status

MAREF is in active development, released under Apache 2.0. 4,300+ tests, 82% code coverage. Available on GitHub at github.com/maref-org/maref.