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 execution authorization for AI agents and automation systems
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.
Draco-Tech is the identity and authorization layer that lets autonomous agents operate with zero static credentials and full policy adherence.
Runtime guardrails for TypeScript AI agents. Prevents duplicate tool calls, enforces per-user cost budgets, and gates irreversible actions. MIT.
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.
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 never holds more than its parent's authority, with an offline-verifiable audit ledger. Python + TypeScript, 18 framework adapters.
EVVM user validators using the ERC-8004 Identity Registry for agent authorization and whitelist management.
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.
To associate your repository with the agent-authorization topic, visit your repo's landing page and select "manage topics."