policy-engine

AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.

Deterministic safety solutions for probabilistic AI agents

Plug IaC governance into any IaC pipeline. Evaluate plans with Tirith, protect sensitive values, enforce centralised policies, and surface actionable results before infrastructure changes are applied.

Agent Execution Partnership AEE is an open-source control plane that ensures every AI agent action is authorized before it runs, observable while it runs, and verifiable after it completes.

Open Source Reliability Harness: Make your agents follow rules. One line of code to‎ ‎enforce, trace, and improve. ‎ ‎

AgentGuard: Zero-Trust Security Foundation for AI Agents

[DEPRECATED] Moved to microsoft/agent-governance-toolkit

RBAC/ABAC/ReBAC policy engine for Python with policy sets, condition DSL, and hot reload

The gate between an AI agent and real money. Runtime authorization for financial AI agents: structured intent, deterministic policy, human approval, execute-once gateway, tamper-evident receipts. Open core, Apache-2.0.

Policy-aware field mission orchestration agent with bounded planning, auditable replanning, travel and expense constraints.

Guardrails service for AI agents. Default-deny tool call evaluation with LLM safety analysis, priority-ordered decision matrix, and human-in-the-loop escalations. Session recording, behavioral analysis, MCP proxy, secret redaction, and real-time audit.

SHACKLE — a governance protocol and policy-decision daemon for autonomous AI agents. Enforces guardrails, budget/loop limits, and policy constraints in real time, with an audited decision engine, SP-1.0 protocol spec, Rust/TypeScript clients, and SOC2-aligned compliance tooling.

Annona — the sovereign execution kernel for AI agents. Decides where each step runs, enforces it, and records it.

LLM guardrails & prompt injection detection for Python. Auto-instruments LangChain, CrewAI, OpenAI, LiteLLM + 8 more frameworks. PII masking, toxicity detection, policy CI/CD. One line, zero code changes.

Structural security, governance and execution for AI agents: validate actions before they touch files, credentials, network, APIs, or money.

Policy-gated, durable, audited execution for AI agent tool calls. Every action gets a five-verdict policy check, a crash-safe checkpoint, and a tamper-evident audit event — a library, not a server.

🔪 Open-source safety firewall for AI agents. Intercepts tool calls before they execute, enforces YAML policies, and kills dangerous operations in real-time. Works with OpenAI, Anthropic, LangChain, and MCP. She doesn't guard. She kills.

MCP-powered memory, policy, and experience layer for safer AI agents.

Model Database Protocol — intent-based, secure database access for LLMs with schema validation, policy engine, data masking, and MCP server support

Plug IaC governance into any GitHub Actions workflow. Evaluate plans with Tirith, protect sensitive values, enforce centralised policies, and surface actionable results before infrastructure changes are applied.