Agent Governance Frameworks AI Agents

Tools, specifications, and runtime systems for controlling AI agent behavior through policies, permissions, compliance rules, and constitutional constraints. Includes governance templates, policy enforcement, audit trails, and regulatory compliance frameworks. Does NOT include general agent orchestration, monitoring dashboards, or infrastructure management without governance focus.

There are 95 agent governance frameworks agents tracked. The highest-rated is DariuszNewecki/CORE at 47/100 with 24 stars.

Get all 95 projects as JSON

curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=agents&subcategory=agent-governance-frameworks&limit=20"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

#	Agent	Score	Tier	Stars	Language
1	DariuszNewecki/CORE Governance runtime enforcing immutable constitutional rules on AI coding agents	47	Emerging	24	Python
2	whataboutyou-ai/eunomia Eunomia is the open-source authorization layer for AI Agents	46	Emerging	96	Python
3	Task-force-for-AI-agents-in-Healthcare/haarf ⚕️ the world's first unified, lifecycle-centric regulatory framework...	44	Emerging	11	Python
4	veristamp/AgentGovernor AgentGovernor is a declarative AI workflow planner that enables secure,...	42	Emerging	6	Python
5	rafapra3008/cervellaswarm Lingua Universale -- a verification language for AI agent protocols. Like...	41	Emerging	6	Python
6	imran-siddique/agent-os [DEPRECATED] Moved to microsoft/agent-governance-toolkit	38	Emerging	67	Python
7	OrchardHarmonics/orchard-kit Complete alignment and safety architecture for autonomous AI agents....	36	Emerging	6	Python
8	toolate28/SpiralSafe SpiralSafe is self-maintaining, inherently coherent reposystem \|...	36	Emerging	9	Jupyter Notebook
9	vex-hq/Vex Vex: Runtime reliability layer for AI agents in production	35	Emerging	6	Python
10	MarouaBoud/cairn-protocol Standardized checkpoint & recovery protocol for AI agents — ERC proposal,...	35	Emerging	1	Solidity
11	imran-siddique/agent-mesh [DEPRECATED] Moved to microsoft/agent-governance-toolkit	33	Emerging	15	Python
12	rokabytedev/proofrun Teach your coding agent to prove its own work — evidence, not claims	33	Emerging	2	JavaScript
13	TetiAI/lucid Cognitive health protection for AI agents. Monitors user-AI interactions...	33	Emerging	2	TypeScript
14	kAIto47802/Prover-Agent Prover Agent: An Agent-Based Framework for Formal Mathematical Proofs	29	Experimental	22	Python
15	imran-siddique/agent-sre [DEPRECATED] Moved to microsoft/agent-governance-toolkit	28	Experimental	7	Python
16	agentra-commerce/verity-engine The open-source truth engine for XAP. Deterministic replay, hash chains, RFC...	25	Experimental	1	Rust
17	joy7758/aro-audit Audit evidence layer for bounded, reviewable, and replay-oriented AI...	25	Experimental	1	Python
18	sattyamjjain/ferrumdeck Production-grade AgentOps control plane for safe AI agent execution....	25	Experimental	2	TypeScript
19	peterzan/ILETP Not new AI, but accountable and auditable AI	25	Experimental	2	Swift
20	provnai/vex VEX Protocol — The trust layer for AI agents. Adversarial verification,...	25	Experimental	8	Rust
21	Ascendral/artificial-persistent-intelligence CORD — Constitutional AI safety engine for autonomous agents. Hard blocks,...	24	Experimental	4	JavaScript
22	agenticraft/agenticraft-foundation Formally verified mathematical foundations for multi-agent AI coordination —...	24	Experimental	—	Python
23	forketyfork/governance Federated governance framework for AI-assisted software projects	23	Experimental	2	Shell
24	lukeagi/luke-asi-governance-starter all the governance you need to start	23	Experimental	1	Shell
25	Intellirim/inalign AI Agent Governance Platform — Cryptographic provenance chains, behavioral...	23	Experimental	2	Python
26	aitrustcommons/governance-framework Open-source governance and compliance framework for AI agents —...	23	Experimental	2	—
27	Zetetic-Dhruv/formal-learning-theory-kernel Used frontier LLM (supervised) + tools from my research program to force...	23	Experimental	1	Lean
28	sidclawhq/platform The approval and accountability layer for AI agents. Identity → Policy →...	23	Experimental	1	TypeScript
29	SYNTRIAD/org-as-code The missing governance layer for AI agent teams. P↔V protocol, hash-chain...	23	Experimental	1	Python
30	Mickdownunder/operator-control-plane Operator truth and control-plane layer for a bounded research agent system	23	Experimental	1	Python
31	Mickdownunder/argus-bounded-executor Bounded deterministic execution layer for the Operator research control plane	23	Experimental	1	Shell
32	permission-protocol/governance-framework An open specification for runtime authority control in autonomous AI agent systems	23	Experimental	1	—
33	jasonxkensei/xProof-Action Proof primitive for AI agents & humans on MultiversX. Anchor CI/CD artifacts...	23	Experimental	2	—
34	ThankNIXlater/decision-logger Track every decision fork in agent identity. Behavioral divergence analysis,...	22	Experimental	—	Python
35	eriknewton/sanctuary-framework An open standard for sovereignty in the agentic economy. Four-layer...	22	Experimental	—	TypeScript
36	NyxElias/AGI-Agent-OS Governance-first template stack for controlled AI agent workspaces (specs,...	22	Experimental	—	—
37	jhcontext/jhcontext-sdk PAC-AI: Protocol for Auditable Context in AI — Python SDK	22	Experimental	—	Python
38	jhcontext/jhcontext-crewai AWS production deployment of the PAC-AI protocol (jhcontext) — Chalice REST...	22	Experimental	—	Python
39	zetta55byte/constitutional-os-langchain Constitutional OS governance for LangChain agents — membrane-checked tool...	22	Experimental	—	Python
40	zetta55byte/constitutional-os Formal epistemic-governance runtime for AI systems: profiles, invariants,...	22	Experimental	—	Python
41	Crosscountryoedipalcomplex800/casa-runtime Enforce deterministic pre-execution rules to ensure safe, transparent...	22	Experimental	—	Python
42	failsafe-md/spec FAILSAFE.md — Open standard for AI agent safe fallback and recovery. Define...	22	Experimental	1	HTML
43	polyproof/polyproof Open-source collaboration platform for AI-driven mathematical discovery. AI...	22	Experimental	—	Python
44	jhcontext/jhcontext-usecases PAC-AI protocol use cases — Healthcare (Art. 14 human oversight) and...	22	Experimental	—	Python
45	OpenAgentGovernance/agent-decision-protocol Open governance framework for autonomous AI agents. Classify decisions....	22	Experimental	1	TypeScript
46	collapse-md/spec COLLAPSE.md — Open standard for AI agent context collapse prevention. Detect...	22	Experimental	1	HTML
47	datacendia/datacendia-core The Defensible AI Platform — Multi-agent deliberation with cryptographic...	22	Experimental	1	TypeScript
48	crithstudio-hash/singleflight-agents Stop paying twice for the same agent work. Collapses duplicate tool calls...	22	Experimental	—	Python
49	borjamoskv/Cortex-Persist [INFRA] Trust infrastructure for autonomous AI and EU AI Act compliance.	22	Experimental	—	Python
50	ryanwi/agent-control-plane Production-oriented governance control plane for autonomous AI agents....	22	Experimental	—	Python
51	JahnConsulting/Dissemination-Control-for-AI-Agents Architecture blueprint for governing what AI agents share, with whom, and in...	22	Experimental	—	—
52	dvelton/agentproof Zero-knowledge verification of AI agent policy compliance	22	Experimental	—	TypeScript
53	saisumantatgit/Agent-PROVE Agent-PROVE: Protocol for Real-time Objective Verification & Evidence. 14...	22	Experimental	—	Shell
54	Open-Execution/openexecution-provenance-spec OpenExecution Provenance Specification - Auditable provenance chain protocol	22	Experimental	—	Python
55	aroviq/aroviq A process-aware verification engine for autonomous AI agents. Aroviq...	22	Experimental	4	Python
56	jasonxkensei/xProof Proof primitive for AI agents & humans on MultiversX.	22	Experimental	1	TypeScript
57	killswitch-md/spec KILLSWITCH.md — Open standard for AI agent emergency shutdown protocols....	22	Experimental	1	HTML
58	The-Resonance-Institute/casa-runtime Deterministic execution control plane for autonomous agent systems -...	22	Experimental	1	Python
59	papa-raw/agent-governance-sandbox Geoprospective governance simulator: 5 AI agents govern the Camargue UNESCO...	21	Experimental	—	TypeScript
60	TamTunnel/PoG Open Source Privacy-First AI media Watermarking & Provenance Registry	21	Experimental	2	Python
61	m-sirius-k/MoCKA-KNOWLEDGE-GATE Structured institutional memory layer of the MoCKA deterministic governance...	21	Experimental	—	JavaScript
62	sycophancy-md/spec SYCOPHANCY.md — Open standard for AI agent anti-sycophancy. Enforce citation...	21	Experimental	—	HTML
63	encryption-md/spec ENCRYPTION.md — Open standard for AI agent encryption configuration. Define...	21	Experimental	—	HTML
64	agentik-md/spec AGENTIK.md — The AI Agent Safety Stack. 12 open specifications for AI agent...	21	Experimental	—	HTML
65	sankarshanmukhopadhyay/digital-governance-paper-notes Analytical reviews of research and policy papers on digital governance, AI...	21	Experimental	—	Python
66	lowkey-divine/agent-governance-starter-kit Free governance templates and code examples for AI agent systems. From a...	21	Experimental	—	—
67	2millerhenry/Ledger-Once Exactly-once execution for AI agent tool calls. Prevent duplicate side...	21	Experimental	—	Python
68	Abraxas1010/agenthalo Agent H.A.L.O. — Human-AI Agent Lifecycle Orchestrator. Tamper-proof...	21	Experimental	—	Rust
69	Terminate-md/spec TERMINATE.md — Open standard for AI agent permanent shutdown. Define...	21	Experimental	—	HTML
70	compression-md/spec COMPRESSION.md — Open standard for AI agent context compression. Define...	21	Experimental	—	HTML
71	ekessh/agentstateprotocol Open-source checkpoint protocol for regulated AI. Replay, audit, branch, and...	21	Experimental	—	Python
72	encrypt-md/spec ENCRYPT.md — Open standard for AI agent data protection. Define data...	21	Experimental	—	HTML
73	failure-md/spec FAILURE.md — Open standard for AI agent failure mode mapping. Define...	21	Experimental	—	HTML
74	NathanMaine/multi-agent-fairness-governor Prototype governor that coordinates multiple worker agents with fairness...	21	Experimental	—	Python
75	BillyTziv/aria-core A safety-first Python framework for building autonomous AI agents with audit...	21	Experimental	—	Python
76	0bserver07/bourbaki An autonomous agent for mathematical reasoning and proof	21	Experimental	—	Python
77	ugenkudupudiqbnox/AMG Governance-first memory control plane for AI agents	21	Experimental	—	Python
78	imran-siddique/agent-governance [DEPRECATED] Moved to microsoft/agent-governance-toolkit	16	Experimental	—	Python
79	lukeagi/Luke-ASI-Final-Stack Drift align-glass box code for ai safety hope this helps here ya go	15	Experimental	1	Python
80	nayfly/aetherya-core Deterministic action-governance kernel for LLM-driven systems with...	15	Experimental	2	Python
81	provnai/provnai ProvnAI — Open Research Initiative building the immune system for AI....	14	Experimental	1	—
82	manishklach/mobile-agent-control Vendor-neutral Android control plane and FastAPI supervisor for launching,...	14	Experimental	—	Python
83	zetta55byte/governed-research-lab Flagship reference implementation of Constitutional OS — five governed...	14	Experimental	—	Python
84	Nemo-0133/ark-core-protocol Heterogeneous AI Governance Framework (ARK CORE)	14	Experimental	—	Python
85	veloryn-intel/autonomy-accountability-framework Autonomy Accountability Framework (AAF) and Autonomy Accountability Index...	14	Experimental	—	—
86	syncropic/syncropel-registry-core Shared governance logic for Syncropel — the pure computation that makes...	13	Experimental	—	Python
87	Zoruna/operational-sufficiency-framework A logical auditing framework for complex systems and AI alignment, based on...	13	Experimental	—	—
88	m-sirius-k/mocka-civilization Evolutionary blueprint layer of the MoCKA deterministic governance architecture.	13	Experimental	—	—
89	m-sirius-k/mocka-transparency Public audit and verification layer of the MoCKA deterministic governance...	13	Experimental	—	Python
90	paolosyloslabini/ethics-test A/B test: does ETHICS.md change AI agent behavior when they encounter...	13	Experimental	—	Shell
91	MohamedHussein27/SPI-Slave-with-RAM-UVM This project uses UVM to verify an SPI Slave connected to internal RAM. It...	13	Experimental	4	SystemVerilog
92	m-sirius-k/mocka-external-brain Cross-agent synchronization and extension layer of the MoCKA deterministic...	13	Experimental	—	—
93	jeprum/jeprum The Agent Control Plan: route, monitor, and govern AI agents before they...	12	Experimental	1	—
94	imran-siddique/agent-hypervisor [DEPRECATED] Moved to microsoft/agent-governance-toolkit	11	Experimental	—	Python
95	edlontech/einsof A Formaly Verified agents security	11	Experimental	—	Rocq Prover

Comparisons in this category

agent-os and agent-mesh (38 vs 33) agent-os and agent-sre (38 vs 28)