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.
Deterministic authorization + tamper-evident audit for AI agents, humans, and workloads — one principal type, safety invariants machine-checked by an SMT solver (cvc5), every decision independently verifiable offline. Pure Rust.
Authorization, delegation, provenance, and verifiable-audit engine for AI agents. MCP adapter published.
Runtime guardrails for TypeScript AI agents. Prevents duplicate tool calls, enforces per-user cost budgets, and gates irreversible actions. MIT.
Draco-Tech is the identity and authorization layer that lets autonomous agents operate with zero static credentials and full policy adherence.
Attenu Derive: computes the permission set each AI agent task needs from the app itself — roster, tools, observed calls — for attenu-guard to enforce on every tool call and sub-agent handoff.
Watch AI agents get stopped. Runnable references for Ratify Protocol: a principal signs a bounded mandate, and the system carrying the consequence verifies it before acting.
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
Attenu Guard for TypeScript — per-agent permissions on every tool call and sub-agent handoff (a sub-agent never holds more than its parent) with a hash-chained audit log verified offline; same bundle format as the Python library.
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.
In-process permission enforcement for AI-agent delegation chains: a sub-agent gets a strict subset of its parent's authority, with an offline-verifiable audit ledger. Python + TypeScript, 18 framework adapters.
Java implementation of the AAuth protocol: RFC 9421 HTTP Message Signatures + JWT proof-of-possession tokens for agent-to-resource authorization
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.
Open security assurance registry and trust center for AI agents, MCP servers, agent identity, authorization, governance, compliance evidence, and continuous verification.
A reference implementation of a stateful, HITL-aware, parameter-bound bridge between A2A and MCP.
OAuth-style delegated authorization for AI agents and MCP servers — scoped, revocable, short-lived tokens.
To associate your repository with the agent-authorization topic, visit your repo's landing page and select "manage topics."