Open-source runtime security and governance for AI agents, MCP tools, robotics, industrial automation, and physical AI.

Runtime authorization & audit layer for physical AI — T0–T3 tiers, capability tokens, Ed25519, ROS2/MCP/MAVLink bridges, OWASP ASI coverage

Runtime identity for AI agents. Short-lived attested credentials with capability tokens that agents narrow as tasks change and verify offline.

Cryptographic verification for AI agent actions — ECDSA-secp256k1 + RFC 6979 signed Action Receipts (v0.1), multi-dimensional Trust Vector, capability tokens (JWT-shaped + Biscuit-style attenuation), UETA §10(b) undo. 29 MCP tools. A2A v1.0 + ERC-8004 format compatible. Receipt-batch Merkle roots anchored on Base mainnet. Starting with code.

Tokfence is the local security daemon that keeps AI agent API keys in an encrypted vault, injects them at request time, and enforces budgets, rate limits, and adaptive risk controls — so your keys never touch agent config files again.

Bounded authorization for AI agents — delegatable capability tokens with cascading revocation + spend-policy verdicts

Agent policy layer for safe tool use across MCP, A2A, and orchestrated agents.

Grantz provides capability token primitives.

AMI — Agent Mobile Identity Protocol. Let an AI agent request, contract (real KYC), activate and operate a real mobile identity — number, voice, SMS, data — over MCP (28 tools) and a REST API. Identity + fine-grained permissions for agents, on top of MCP and A2A.

AsiBackbone is a .NET package-family project providing framework-neutral governance primitives for consequential software decision flow, including actor context, constraint evaluation, governance decisions, audit residue, and acknowledgment handshakes.