Open-source runtime security and governance for AI agents, MCP tools, robotics, industrial automation, and physical AI.
-
Updated
Aug 12, 2026 - TypeScript
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
Each agent run gets its own short-lived attested credential. A stolen token is not enough.
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.
Production authorization and human-approval for AI agents, with scoped capability tokens, spend policies, Telegram review, and x402 Pay-to-Claim.
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.
Agent policy layer for safe tool use across MCP, A2A, and orchestrated agents.
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.
Citizen-side control layer for AI-agent delegation on the AI Passport: scoped purpose-bound capability tokens, provable revocation via introspection (RFC 7662), and a hash-chained receipt ledger. Real Web Crypto, zero dependencies. AI Passport Ideathon.
Grantz provides capability token primitives.
Practical .NET architecture tutorials, labs, and reference patterns for governed execution, secure applications, AI integration, and policy-driven systems.
A .NET governance and policy-control framework for auditable AI and enterprise decision flows: policy-as-code, capability tokens, acknowledgment workflows, and host-owned execution.
Add a description, image, and links to the capability-tokens topic page so that developers can more easily learn about it.
To associate your repository with the capability-tokens topic, visit your repo's landing page and select "manage topics."