Governance gateway for AI agents — bounded, auditable, session-aware control with MCP proxy, shell proxy & HTTP API. Works with Cursor, Claude Code, Codex, and any MCP-compatible agent.

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

OpenTelemetry-based tracing SDK for AI agents and LLM applications

JSON Agents - A universal JSON-native standard for describing AI agents, their capabilities, tools, runtimes, and governance in a portable, framework-agnostic format. Based on RFC 8259, JSON Schema 2020-12.

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

AI got hands. This is the leash. Policy, audit, kill switch for any AI agent with access to your accounts.

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

Stop Claude Code from doing irreversible damage. Policy-gated execution + receipts so you can ship agents without sweating production.

AgentGovernor is a declarative AI workflow planner that enables secure, auditable, and cost-efficient MCP tool execution through validated PlanYAML workflows.

A decentralized protocol for agent trust, dialogue, and influence in open multi-agent systems.

🛡️ A curated list of tools, frameworks, standards, and resources for AI agent governance, safety, and compliance

A protocol engine for governing AI agent workflows through spec driven work and checkpoints.

Execution safety & governance layer for AI agents: idempotency, budgets, tool control, audit logs.

Enterprise-grade governance and policy enforcement for agentic AI systems.

Signed receipts for agent/tool actions. PolicyGate enforces allow/deny; every decision emits a tamper-evident receipt with hashes, signatures, and optional approvals. Verify in CI, prove what happened, and make agent integrations survivable in regulated environments.

Architecture research exploring capability-tiered AI governance and compute-linked enforcement protocols.

Declarative specification for AI agents to publish identity, capabilities and operational boundaries before interaction.

Sovereign AI governance interface for capsule-based agent ecosystems. Patent-backed. SLPL licensed.

Asia's first AI-governed horror venue RWA. 1.33x Rent Coverage. Real-time POS Data Oracle for Global Treasuries.

Deterministic execution boundary for AI systems enforcing signed approvals, replay protection, and cryptographic receipts.

Production-ready safety framework preventing identity fusion, synthetic intimacy, and unbounded behavior in AI agent systems. Machine-readable contracts and verse-lang primitives for immediate deployment.

Mathematical governance framework for AI agents — deterministic fidelity scoring, cryptographic audit trails, 15-25ms per decision

Wise Governance for AI Agents - Provides governance, traceability, and auditability for OpenClaw, LangChain, AutoGPT, and more.

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

MCP server for AI agent governance. Pre-execution tool call validation, drift detection, circuit breakers, human-in-the-loop holds. Sub-millisecond latency.

Constrained autonomy runtime for AI agents.

Policy enforcement for AI agent tool calls — allow, approve, or deny with audit trail

Memory and document governance framework for multi-agent OpenClaw teams

Canonical spec + RFCs for Agent Authority Protocol (AAP): human authority, proposal/evidence lifecycle, auditable world-state transitions.

Desktop gateway for Agent Governor. Drag-and-drop governance for the rest of us.