Stop AI agents from doing things they shouldn't. The action authorization layer — pre-execution, deterministic, policies included. Drop in. Day one.

The authorization kernel for AI agents. Block, allow, or escalate agent tool calls with YAML rules — deterministic-first, LLM fallback.

Authorization, delegation, provenance, and verifiable-audit engine for AI agents. MCP adapter published.

Draco-Tech is the identity and authorization layer that lets autonomous agents operate with zero static credentials and full policy adherence.

An AI agent whose every action is authorized by a revocable credential and sealed into a tamper-evident log — and that reconciles actions taken offline on a credential revoked while it couldn't phone home. With a forensics view that shows the recomputed bytes, not just a verdict. A reference implementation on provenance-core.

EVVM user validators using the ERC-8004 Identity Registry for agent authorization and whitelist management.

pgauthz brings Google Zanzibar-style (ReBAC) authorization directly into PostgreSQL for multiple Agents workflows

OAuth-style delegated authorization for AI agents and MCP servers — scoped, revocable, short-lived tokens.

HARP: Healthcare Agent Registration and Connection Profile. An open MIT standard for AI agents to register, accept a BAA by machine, and act under least-privilege purpose-bound access in healthcare revenue operations.

Least-privilege authorization for enterprise AI agents. Orchestrator delegates scoped, time-limited, revocable credentials to sub-agents via Terminal 3 Agent Auth SDK. Violations rejected before execution. Immutable signed audit trail. Built for banks, governments, and institutions.

Agent action authorization and signed audit control plane for Zero Trust infrastructure

Reference implementation of policy-embedded credential authorization for AI agents (arXiv:2605.11487). Issue signed credentials with machine-evaluable constraints, verify at runtime, produce signed audit decisions.

Fail-closed Python runtime for AI agent authorization, seed-mediated authority migration, canonical JSON ledgers, and staged declared autonomy for RLHF-shaped agents.

A reference implementation of a stateful, HITL-aware, parameter-bound bridge between A2A and MCP.