Agent Authorization Guardrails AI Agents

Runtime policy enforcement and action validation systems that intercept, inspect, and control AI agent tool calls before execution. Includes deterministic allowlists, policy gates, audit layers, and access control frameworks. Does NOT include general agent monitoring, logging dashboards, or post-execution incident response systems.

There are 245 agent authorization guardrails agents tracked. 12 score above 50 (established tier). The highest-rated is microsoft/agent-governance-toolkit at 64/100 with 47 stars and 4,254 monthly downloads. 1 of the top 10 are actively maintained.

Get all 245 projects as JSON

curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=agents&subcategory=agent-authorization-guardrails&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	microsoft/agent-governance-toolkit AI Agent Governance Toolkit — Policy enforcement, zero-trust identity,...	64	Established	47	Python
2	ucsandman/DashClaw 🛡️Decision infrastructure for AI agents. Intercept actions, enforce guard...	61	Established	121	JavaScript
3	mattijsmoens/sovereign-shield AI security framework: tamper-proof action auditing, prompt injection...	59	Established	15	Python
4	vstorm-co/pydantic-ai-middleware Middleware layer for Pydantic AI — intercept, transform & guard agent calls...	59	Established	22	Python
5	vstorm-co/pydantic-ai-shields Guardrail capabilities for Pydantic AI — cost tracking, prompt injection...	58	Established	27	Python
6	Pro-GenAI/Agent-Action-Guard 🛡️ Safe AI Agents through Action Classifier	57	Established	7	Python
7	Dicklesworthstone/destructive_command_guard The Destructive Command Guard (dcg) is for blocking dangerous git and shell...	56	Established	670	Rust
8	akios-ai/akios Secure runtime for multi-agent AI. Kernel sandboxing (seccomp-bpf),...	56	Established	5	Python
9	galaar-org/AgentARC Security & policy enforcement layer for AI blockchain agents with...	52	Established	5	Python
10	secretgate/secretgate Security proxy for AI coding agents — intercepts outbound traffic and...	51	Established	9	Python
11	kahalewai/agent-context-guard Control Plane Integrity Tool for AI Agents. Cryptographically seal, verify,...	50	Established	6	Python
12	mattijsmoens/intentshield Pre-execution intent verification for AI agents. Audits what your AI is...	50	Established	17	Python
13	project-codeguard/rules Project CodeGuard is an AI model-agnostic security framework and ruleset...	47	Emerging	394	Python
14	antropos17/Aegis Open-source EDR for AI agents. Monitor processes, files, network, and...	47	Emerging	94	JavaScript
15	ZenGuard-AI/fast-llm-security-guardrails The fastest Trust Layer for AI Agents	45	Emerging	152	Python
16	Justin0504/Aegis Runtime policy enforcement for AI agents. Cryptographic audit trail,...	43	Emerging	200	TypeScript
17	luckyPipewrench/pipelock Firewall for AI agents. DLP scanning, SSRF protection, bidirectional MCP...	43	Emerging	217	Go
18	railyard-dev/railguard Safe runtime for Claude Code, built to be yours.	42	Emerging	26	Rust
19	ylu999/jingu-trust-gate jingu-trust-gate – deterministic admission layer that blocks LLM...	42	Emerging	3	TypeScript
20	preloop/preloop Preloop is the Safety Layer for AI agents: MCP firewall, human approvals,...	41	Emerging	6	Python
21	alifanov/scopegate AI Access Proxy Layer — granular permission gateway for AI agents. Connect...	40	Emerging	9	TypeScript
22	mukul975/Privacy-Data-Protection-Skills 282+ structured privacy & data protection skills for AI agents. GDPR, CCPA,...	40	Emerging	34	Python
23	kahalewai/agbac AGent Based Access Control (AGBAC) is is an open, vendor-neutral security...	40	Emerging	7	—
24	teluashish0/sec0-sdk Open-source runtime safety enforcement and data curation SDK for safe,...	40	Emerging	3	TypeScript
25	vmehera123/leashd Safety-first agentic coding framework. Three-layer safety pipeline (sandbox,...	40	Emerging	2	Python
26	arch3rPro/Trae-Proxy An intelligent API proxy tool designed to intercept and redirect OpenAI API...	40	Emerging	99	Python
27	edictum-ai/edictum Runtime governance for AI agents. Contracts enforce what tools can do —...	38	Emerging	13	Python
28	aporthq/aport-agent-guardrails Pre-action authorization guardrails for AI agents - Works with OpenClaw,...	38	Emerging	15	Shell
29	guard0-ai/g0 The control layer for AI agents. 1,200+ rules, 12 domains, 10 frameworks,...	38	Emerging	24	TypeScript
30	PlawIO/veto The authorization kernel for AI agents. Block, allow, or escalate agent tool...	38	Emerging	5	TypeScript
31	invariantlabs-ai/invariant-gateway LLM proxy to observe and debug what your AI agents are doing.	37	Emerging	68	Python
32	liuhaotian2024-prog/K9Audit Engineering-grade causal audit infrastructure for AI agents	37	Emerging	3	Python
33	unwind-mcp/unwind Deterministic security engine for AI agents. See, block, rewind, prove.	37	Emerging	2	Python
34	Threat-Vector-Security/guardian-agent Security-first AI agent orchestration system. Built-in agents with...	37	Emerging	3	TypeScript
35	anormang1992/vre Volute Reasoning Engine (VRE): Structural Epistemic Enforcement for Agentic AI	36	Emerging	6	Python
36	TorbenWetter/agentpass An execution gateway for AI agents on untrusted devices. Agents request,...	36	Emerging	3	Python
37	Acacian/aegis Open-source policy engine + approval gate + audit log for AI agents. YAML...	35	Emerging	1	Python
38	epappas/llmtrace Zero-code LLM security & observability proxy. Real-time prompt injection...	35	Emerging	35	Rust
39	X-Scale-AI/GRITS Open-source AI agent security framework. Score, harden, and govern your AI...	35	Emerging	9	—
40	Cohorte-ai/trustgate Black-box AI reliability certification via self-consistency sampling and...	34	Emerging	10	Python
41	Agent-Sudo-Org/agent-sudo The missing safety layer for AI Agents. Adaptive High-Friction Guardrails...	34	Emerging	4	TypeScript
42	artoo-corporation/D2-Python Detect and Deny - Deterministic Function-Level Guardrails for AI Agents	34	Emerging	17	Python
43	pohi-protocol/pohi Proof of Human Intent (PoHI) - Cryptographically verifiable human approval...	33	Emerging	18	TypeScript
44	anchorco/anchor-scan AST-based governance pattern scanner for AI agent code. Detects compliance...	33	Emerging	2	Python
45	chaukasai/chaukas-sdk One line to instrument your agent and capture every event in an immutable,...	33	Emerging	2	Python
46	dormstern/leashed AI got hands. This is the leash. Policy, audit, kill switch for any AI agent...	33	Emerging	12	TypeScript
47	agent-wall/agent-wall Security firewall for AI agents. Intercepts MCP tool calls, enforces...	33	Emerging	6	TypeScript
48	vectimus/vectimus Deterministic governance for AI coding agents. Cedar-based policy engine...	32	Emerging	22	Python
49	llm-platform-security/SecGPT An Execution Isolation Architecture for LLM-Based Agentic Systems	32	Emerging	107	Python
50	bluvibytes/zone-of-distrust Open security architecture for autonomous AI agents - extending Zero Trust principles	32	Emerging	7	—
51	GitsSaikat/Guardian-Agent Improving AI Systems with Self-Defense Mechanisms	32	Emerging	23	Python
52	amsminn/vericontext Deterministic, hash-based verification for docs that reference code....	32	Emerging	7	TypeScript
53	kahalewai/agent-policy-engine Agent Policy Engine is an AI agent enforcement runtime (PEP) that prevents...	32	Emerging	7	Python
54	ashutosh-stark/velocity-gate High-performance AI Firewall for Spring Boot. Detects and blocks headless...	32	Emerging	1	Java
55	AxonLabsDev/BodAIGuard Universal AI agent guardrail. Prevents AI agents from executing dangerous...	32	Emerging	1	—
56	chaukasai/chaukas-spec Canonical proto3 definitions for Chaukas: audit events, traces, decisions,...	30	Emerging	3	Makefile
57	sawzhang/silicon_agent Multi-agent AI system with sandbox isolation, role-based execution, and...	29	Experimental	3	Python
58	somegg90-blip/quiguard-gateway The self-hosted security firewall for AI Agents. Scrubs PII from prompts and...	28	Experimental	6	Python
59	Szesnasty/ai-protector Self-hosted LLM firewall and agent guardrails that block prompt injection,...	27	Experimental	11	Python
60	airblackbox/gateway AI governance control plane — EU AI Act compliance, AI-BOM, shadow AI...	27	Experimental	10	Go
61	rahuliitk/quicktrust Open-source, agent-first GRC platform — fast, affordable compliance...	26	Experimental	8	Python
62	ZhengYeah/AudAgent [PETS'26] AudAgent: Automated Auditing of Privacy Policy Compliance in AI Agents	26	Experimental	6	Python
63	backbay-labs/hush Portable security rules for the tool boundary of AI agents	26	Experimental	7	Rust
64	radoslaw-sz/guardio Guardio is a proxy that sits between your AI Agent system and the external world	26	Experimental	5	TypeScript
65	ubcent/velar Local Privacy Firewall for AI	26	Experimental	5	Go
66	azender1/SafeAgent SafeAgent — deterministic execution guard for AI agents. Finality gating +...	25	Experimental	4	Python
67	markamo/envpod-ce Zero-trust governance environments for AI agents	25	Experimental	3	Rust
68	rjc25/SnoutGuard Architectural guardrails for AI coding agents	25	Experimental	4	TypeScript
69	ax128/AegisGate Open-source security gateway for LLM APIs — prompt injection detection, PII...	25	Experimental	4	Python
70	AriKernel/arikernel Runtime security layer for AI agents — enforces policy on tool calls to help...	25	Experimental	3	TypeScript
71	PredicateSystems/predicate-authority-sidecar The work visa for AI agents. A high-performance Rust sidecar that...	25	Experimental	4	Rust
72	jensabrahamsson/overblick Security-first multi-identity agent framework with personality stable,...	24	Experimental	2	Python
73	jzOcb/agent-guardrails Mechanical enforcement tools to prevent AI agents from bypassing established...	24	Experimental	10	Shell
74	Chimera-Protocol/chimera-runtime The deterministic constraint layer for autonomous AI agents. Enforce...	24	Experimental	2	Python
75	repoforge-dev/authority-layer Runtime guardrails for AI agents that enforce token budgets, loop limits,...	24	Experimental	2	TypeScript
76	NuGuardAI/nuguard opensource repo for NuGuard	24	Experimental	2	Python
77	hakandamar/ct-toolkit Identity Continuity Guardrails for Agentic Systems: An open-source...	24	Experimental	2	Python
78	mustafadakhel/oag Portable runtime policy and audit layer for AI agents - HTTP/HTTPS proxy...	24	Experimental	2	Kotlin
79	OnceOnly-Tech/onceonly-python Execution safety & governance layer for AI agents: idempotency, budgets,...	23	Experimental	1	Python
80	izumi0214/SAFE-AI-License 🤖 Foster responsible AI development with the SAFE-AI License, ensuring...	23	Experimental	1	—
81	kanson1996/agent-audit-trail 🔍 面向 AI Agent 的防篡改审计溯源系统 \| Tamper-evident audit trail for AI Agents —...	23	Experimental	1	TypeScript
82	ajpandit775/kaida-shield The secure runtime for AI agents. Run anything. Break nothing.	23	Experimental	1	HTML
83	regen-dev/agent-safe-guard Native safety hooks for Claude Code — blocks destructive commands, enforces...	23	Experimental	1	C++
84	myles1663/lancelot A Governed Autonomous System — constitutional governance, risk-tiered...	23	Experimental	1	Python
85	lixian-shu/AgentGate Runtime security for autonomous AI agents — policy enforcement, audit trail,...	23	Experimental	1	Python
86	DilawarShafiq/unworldly The flight recorder for AI agents. Tamper-proof, ISO 42001 + HIPAA-compliant...	23	Experimental	5	Python
87	AlethiaQuizForge/no-hallucination Stop your AI from hallucinating its own history. Session discipline for...	23	Experimental	1	Shell
88	nnennandukwe/policyNIM PolicyNIM is a policy-aware engineering preflight layer for AI coding agents.	23	Experimental	1	Python
89	FloHofstetter/shoreguard Open source control plane for NVIDIA OpenShell	23	Experimental	1	Python
90	Sachin-Buluswar/reentbot LLM agent harness for auditing Solidity smart contracts with static...	23	Experimental	1	Python
91	nopemd/nope.md Define what your agent can't do. Because if it gets compromised, those...	23	Experimental	6	JavaScript
92	enkronos/guardmesh GuardMesh — Portable policy checks for governed agent execution.	23	Experimental	1	TypeScript
93	AnkitSharma-29/qutato A high-performance trust layer for agentic workflows. Qutato provides...	23	Experimental	1	Python
94	kawarimidoll/guard-and-guide 🛡️ Guard coding agents from dangerous operations, and 🧭 Guide them to safer...	23	Experimental	1	Rust
95	xsa520/guardian Governance infrastructure for autonomous AI agents. Policy enforcement,...	23	Experimental	1	Python
96	dimitarrskv/thundergate Thundergate — real-time execution firewall for autonomous AI agents....	23	Experimental	1	TypeScript
97	CipherandRow/cr-gateway AI output validation API. Check integrity, kill bad agent chains, compress...	23	Experimental	1	—
98	AgentSteer/AgentSteer Runtime protection for AI coding agents. Intercepts tool calls, scores them...	23	Experimental	1	TypeScript
99	matank001/copilot-agents-guard LLM-as-a-Judge security layer for Microsoft Copilot Studio agents	23	Experimental	10	Python
100	tobs-code/policy-gate Deterministic allowlist-first policy gate for LLM applications, agents, and...	23	Experimental	1	Rust
101	ian-flores/secureguard Input, code, and output guardrails for R LLM agents	22	Experimental	—	R
102	lowkey-divine/agent-governance-check Five governance questions for your AI agent system. Scan any repo in thirty...	22	Experimental	—	JavaScript
103	npow/rampart Durable LLM agent runtime — crash recovery, budget limits, and permission...	22	Experimental	—	Python
104	crithstudio-hash/agent-guard Block prompt injection, path traversal, SQL injection, and more — before...	22	Experimental	—	Python
105	agenerationforwordz-tech/supersafe AI agent file quarantine system - isolate downloaded files on removable...	22	Experimental	3	PowerShell
106	pboueke/carranca Isolated agent runtime with verified audits, deep observability, policy...	22	Experimental	—	Shell
107	ylqxb/MirageShield MirageShield \| AI multi-agent driven active cyber defense system, with...	22	Experimental	—	HTML
108	QuartzUnit/agent-action-policy Declarative action policies for AI agents — composable templates for safe...	22	Experimental	—	Python
109	Tuckerfixed667/railguard Provide a safe runtime environment for Claude code with Railguard, ensuring...	22	Experimental	—	Rust
110	Fozikio/reflex Fork of Anthropic's hookify plugin — adds graduated enforcement...	22	Experimental	—	JavaScript
111	Starlight143/langgraph-stage0-gate Stage0 authorization gate for LangGraph agents with Human-in-the-Loop...	22	Experimental	—	TypeScript
112	jamesburchill/safeagent SafeAgent is a Dockerized execution layer for AI agents that enforces...	22	Experimental	—	Python
113	agentscore/python-gate Trust-gating middleware for Python web frameworks (FastAPI, Flask, Django)...	22	Experimental	—	Python
114	seconize-co/dhi Dhi - Runtime Intelligence & Protection System. Sanskrit: Intellect \|...	22	Experimental	—	Rust
115	StanislavBG/agent-comply EU AI Act compliance scanner for AI agents — static analysis, Annex III risk...	22	Experimental	—	TypeScript
116	StanislavBG/agent-gate Pre-deploy readiness gate for AI agents — runs stepproof + agent-comply +...	22	Experimental	—	TypeScript
117	ismailkarabulut-lang/theia-guard Approval-based execution layer for AI agents. Enforces human-in-the-loop...	22	Experimental	—	Python
118	thulisa-n/pki-compliance-gate Automated PKI Compliance Engine for X.509 certificates. Implementing...	22	Experimental	—	Python
119	Qwayk/plausible-api-tool Safe-by-default CLI for Plausible Analytics APIs (plan-first, apply-gated...	22	Experimental	—	Python
120	Qwayk/amazon-pa-api-tool Read-only CLI for Amazon Product Advertising API (PA-API v5),...	22	Experimental	—	Python
121	VamsiSudhakaran1/release-gate 🚪 Governance gate for AI agents. Enforce policies before deployment: request...	22	Experimental	—	HTML
122	iuriikogan/Audit-Agent Multi-Agent Compliance Security Platform (CRA & DORA) A scalable,...	22	Experimental	—	Go
123	vineeth0216/alpenguard-security-framework Provide zero-trust security and compliance middleware designed to protect...	22	Experimental	—	Rust
124	PredicateSystems/predicate-secure Secure your AI agents with policy-based authorization. Wraps browser-use,...	22	Experimental	3	Python
125	mnacym/data-steward-agent 🛡️ Streamline data governance for SaaS with the Data Steward Agent, ensuring...	22	Experimental	—	—
126	AakarshakKaushal00/guardrail-layer 🛡️ Safeguard your data with Guardrail Layer, a self-hosted AI system that...	22	Experimental	—	—
127	morgaesis/ssh-guard LLM-powered SSH command filter for AI agents. Evaluate every command before...	22	Experimental	—	Rust
128	LakshmiSravyaVedantham/llm-guard A configurable safety proxy for AI agents — blocks loops, cost overruns,...	22	Experimental	—	Rust
129	Trusted-Autonomy/TrustedAutonomy An agentic governance layer enabling autonomy with human review of results...	22	Experimental	—	Rust
130	michal1314esp/hallucinate.md Enforce a clear, open standard in your codebase that directs AI agents to...	22	Experimental	—	JavaScript
131	roli-lpci/suy-sideguy Runtime safety guard for autonomous AI agents. Watches process, file, and...	22	Experimental	—	Python
132	NAdrian95/ai-agent-security-checklist Comprehensive security checklist for deploying autonomous AI agents safely....	22	Experimental	—	—
133	NeoSkillFactory/rbac-terminal-access Implements role-based access control to limit AI agent terminal access based...	22	Experimental	—	Shell
134	lhy0718/Guardplane Security kernel + sandboxed runner for AI agents	22	Experimental	—	Python
135	EXPESRaza/agent-guardrails-lab A production-style AI agent safety framework demonstrating multi-layer...	22	Experimental	—	Python
136	productstein/antihero Security & Insurance Infrastructure for AI Agents — policy enforcement,...	22	Experimental	—	Python
137	vorionsys/cognigate AI governance enforcement gateway — 692 Python tests, trust scoring, proof chains	22	Experimental	—	Python
138	viplavfauzdar/aisecops-interceptor AISecOps Interceptor — Runtime security layer for AI agents	22	Experimental	—	Python
139	agent2allow/agent2allow Agent2Allow: ship AI agents safely with deny-by-default permissions,...	22	Experimental	—	Python
140	ggsaad82/A2A-Agent-Action-Guard 🛡️ Safeguard AI agents from harmful actions with A2A-Agent-Action-Guard,...	22	Experimental	—	Python
141	evenutbearing94/command-verify 🚀 Verify commands in your markdown files with ease, ensuring documentation...	22	Experimental	—	HTML
142	nikodemus-eth/saoe-mvp Secure Agent Operating Environment — SATL envelopes + ToolGate + red-team...	22	Experimental	—	Python
143	JonathanCGill/airuntimesecurity.io Declare what your AI system should do. Guardrails enforce it. An...	22	Experimental	—	Python
144	LeoLucky1/agent-change-gate Block risky agent capability changes before merge with explicit,...	22	Experimental	—	TypeScript
145	smokee1221/thundergate Control AI actions with Thundergate, a real-time execution firewall that...	22	Experimental	—	TypeScript
146	AaronCx/LastGate AI agent commit guardian — pre-flight checks for AI-generated code. Secret...	22	Experimental	—	TypeScript
147	rjkaes/shush Claude Code safety guard plugin. AST-based bash command classification	22	Experimental	—	JavaScript
148	getactra/actra Action Admission Control for Agentic and Automated Systems	22	Experimental	—	Rust
149	Ghengeaua/AlterSpec Runtime enforcement engine for AI agents — policy evaluation, audit trails,...	22	Experimental	—	Python
150	JuroOravec/safe-ai-factory Safety harness for autonomous AI agents: Spec-driven AI factory. Use with...	22	Experimental	—	TypeScript
151	ElmadaniS/nrp NRP — 6 rules no AI can break. The safety standard for agentic AI. Manifest,...	22	Experimental	—	HTML
152	swiencki/claude-code-guardrails Practical guide to Claude Code's six guardrail layers with ready-to-use examples	22	Experimental	—	Shell
153	sanjeevneo/sparkey Time-limited, self-destructing SSH access for AI agents. Four-layer...	22	Experimental	—	Shell
154	ian-flores/securetools Security-hardened tool definitions for R LLM agents	22	Experimental	—	R
155	SanAntonio021/windows-agent-guardrails Windows-first guardrails for AI agents and terminal-capable assistants, with...	22	Experimental	—	—
156	poyao0705/guardian-angel Policy engine for governing AI agent tool execution.	22	Experimental	—	Python
157	nak-nak1308/verifiable-intent Define and verify cryptographic agent authorization to ensure AI actions...	22	Experimental	—	Python
158	saulinfectious906/Glass-Box Prevent LLM hallucination by enforcing deterministic Python code execution...	22	Experimental	—	Python
159	Cherise1608/agent-shield Governance readiness scanner for AI agent projects — compliance scoring for...	21	Experimental	2	Python
160	nimonkaranurag/agentpolicylayer The standard protocol for defining runtime guardrails for your enterprise...	21	Experimental	2	Python
161	HZYAI/agenthalt Production-grade guardrails for AI agent function calls. Budget, scope,...	20	Experimental	1	Python
162	chitin-id/chitin-shell The missing security layer for AI agents. Open-source middleware separating...	20	Experimental	1	TypeScript
163	PredicateSystems/temporal-predicate-typescript Protect your temporal.io agents with zero-trust runtime authorization. Block...	20	Experimental	1	TypeScript
164	NextStat/GoGuard Zero-tolerance for Go panics. A Rust-powered static analyzer that brings...	20	Experimental	1	Rust
165	Ethan-YS/ai-agent-trust-boundary Why every AI agent is vulnerable to prompt injection — and a proposed...	20	Experimental	1	—
166	facto-ai/facto The audit trail for AI agents. Cryptographic logging for compliance and forensics.	20	Experimental	1	Python
167	AlpenGuard/alpenguard-security-framework AlpenGuard is a security-first middleware layer for autonomous AI agents on...	20	Experimental	1	Rust
168	theios-research-institute/epistemic-guardrails-for-ai-agents Cross-platform epistemic access control for AI coding assistants - Claude...	20	Experimental	1	Shell
169	Igor-ChatGPT/differential-meaning-monitor Semantic differential protection layer for AI agents. The semantic analogue...	19	Experimental	—	Python
170	EM1805/causal-safety-engine Causal safety and AI governance layer that blocks unsafe agent actions...	19	Experimental	—	Python
171	sherifkozman/afl Runtime-agnostic hook harness that catches unverifiable prompts, enforces...	19	Experimental	—	Python
172	DonTrabajo/ProxMesh-Blueprint Public blueprint of a local-first multi-agent security lab (demo + OPSEC gates).	19	Experimental	—	Python
173	TheNovacene/verse-nerves Verse-Nerves (VN-MW) is safety middleware for agentic systems: runtime...	19	Experimental	—	Python
174	grayowlresearch/obol-sdk Trust infrastructure for AI agents — 7-layer on-device detection, privacy-first	19	Experimental	—	Python
175	TheNovacene/verse-ality-agents Production-ready safety framework preventing identity fusion, synthetic...	19	Experimental	—	Python
176	heurema/proofpack Proof-carrying CI gate for AI agent changes	19	Experimental	—	Python
177	A386official/agentguard AI Agent Firewall & Sandbox — Run any AI agent with enforced permissions,...	19	Experimental	—	TypeScript
178	rubixchain/agentdna Verifiable and Auditable AI Agents	19	Experimental	—	Python
179	PredicateSystems/temporal-predicate-py Protect your temporal.io agents with zero-trust runtime authorization. Block...	19	Experimental	—	Python
180	LoFi-Monk/lofi-gate Reduce token usage and prevent agent hallucination by structuring your test...	19	Experimental	—	Python
181	Diomandeee/admissibility-kernel Deterministic context slicing with cryptographic admissibility verification...	19	Experimental	—	Rust
182	preambleai/preamble.md preamble.md is a security policy file that governs AI agent behavior. It...	19	Experimental	—	Shell
183	noumi0k/gg Git & GitHub CLI Guard — prevent dangerous git/gh operations by AI agents	19	Experimental	—	Rust
184	harsharao85/aws-ai-agent-guardrails Validated IAM reference architecture for AI coding agents on AWS. Four-layer...	19	Experimental	—	TypeScript
185	Runestone-Labs/gatekeeper Policy enforcement for AI agent tool calls — allow, approve, or deny with audit trail	19	Experimental	—	TypeScript
186	akz4ol/agent-checkpoint A control plane for AI coding agents that prevents lies and ensures transparency	19	Experimental	—	Shell
187	xoity/AuditAgent Automate firewall policy auditing and enforcement with this AI-driven Python...	18	Experimental	3	Python
188	shazm12/safe-ns AI Content Moderation Tool to detect and flag NSFW images and text.	17	Experimental	2	TypeScript
189	promptshieldhq/promptshield-proxy A free, open-source LLM security proxy. Drop it between your app and any LLM...	17	Experimental	3	Go
190	apierron/baton A composable validation gate for AI agent outputs.	17	Experimental	3	Rust
191	gendigitalinc/aarts An Open Standard for AI Agent Runtime Safety (AARTS)	16	Experimental	12	—
192	pallma-ai/pallma-guard PallmaAI delivers complete, lifecycle security for your AI agents, from...	16	Experimental	11	Python
193	somegg90-blip/ironlayer-gateway The self-hosted security firewall for AI Agents. Scrubs PII from prompts and...	16	Experimental	2	Python
194	Pro-GenAI/A2A-Agent-Action-Guard A2A version of Agent Action Guard: Safe AI Agents through Action Classifier	16	Experimental	1	Python
195	capiscio/langchain-capiscio Trust enforcement for LangChain and LangGraph agents — verify caller badges,...	15	Experimental	1	Python
196	Dr-AneeshJoseph/anvil-safety-framework A multi-agent safety engineering framework that subjects systems to...	15	Experimental	—	Python
197	lokryn-llc/compliance-log-schema Protocol Buffers schema for compliance-grade audit logging. Built for SOC2,...	15	Experimental	—	Python
198	MrunalTalikoti/LandGuard A Orchestration Agent system which detects misleading information and stores...	15	Experimental	—	Python
199	ylu999/jingu-trust-gate-py jingu-trust-gate – deterministic admission layer that blocks LLM...	15	Experimental	1	Python
200	joy7758/verifiable-agent-demo Minimal end-to-end demo for the Digital Biosphere Architecture stack.	15	Experimental	1	Python
201	substrateagnostic/agentledger Compliance Audit Trails for Agents	15	Experimental	—	TypeScript
202	EricEEEEEEE/agent-integrity Runtime audit layer for AI agents — detects hallucination, deception,...	15	Experimental	1	Python
203	ShreyasDasari/trailback The trust, audit, and recovery layer for production AI agents. Intercept...	15	Experimental	1	—
204	aami-dodon/ProjectX Stealth venture building an AI Governance Cloud that automates compliance...	15	Experimental	—	JavaScript
205	az9713/icr 🛡️ Make AI show its work before it does the work. The intent problem? Fixed.	15	Experimental	—	Shell
206	joostme/doubleagent Security gateway for AI agent containers — isolates secrets, enforces HTTP...	15	Experimental	1	Python
207	hummbl-dev/hummbl-assurance Governance assurance for AI agent systems — deterministic verification of...	14	Experimental	—	Python
208	zurbrick/agent-qa-gates Field-tested QA validation gates for AI agent systems. Tiered gates,...	14	Experimental	—	Shell
209	Fulcria-Labs/agentgate AgentGate - Auth0-powered authorization gateway for AI agents. Policy...	14	Experimental	—	Python
210	SignalweaverStudio/signalweaver Deterministic governance layer for AI agents — enforce policies, trace...	14	Experimental	—	Python
211	Amrutha-J822/GuardianAI GuardianAI is an AI-powered disaster safety assistant that detects hazards...	14	Experimental	—	Python
212	Born14/verify Verification gate for AI-generated code. 7-gate pipeline with constraint...	14	Experimental	—	TypeScript
213	SA-Guliy/DecisionGuard Multi-agent governance framework protecting product decisions from toxic...	14	Experimental	—	Python
214	Maperez1972/privaro-proxy Privaro Proxy API: intercepts prompts, applies policies, manages tokenization flow	14	Experimental	—	Python
215	JohnODowdAI/toolpact Enforce tool-usage contracts on agent tool calls — block before side effects.	14	Experimental	—	Python
216	matthiastjong/shellgate The secure gateway for AI agents. One token. Full control. Complete audit trail.	14	Experimental	—	Svelte
217	raulvallejo/make-agent-firewall A reusable Make AI Agent security layer built on OWASP Top 10 for LLM...	14	Experimental	—	—
218	lulzasaur9192/agent-audit-log-examples AI agent audit log examples — tamper-evident HMAC logging, LangChain...	14	Experimental	—	—
219	minhtri22/OPENCLAW-FINANCIAL-GUARDRAIL-SKILL OpenClaw Financial Guard is a financial guardrail layer for agent systems,...	14	Experimental	3	TypeScript
220	RishabhMathur06/Building_AI_Agents_With_Guardrails First, a large-scale unguarded AI system is built which is prone to multiple...	14	Experimental	—	Python
221	danilotpnta/citeguard LLM hallucination detection pipeline for verifying bibliographic references	14	Experimental	—	Python
222	tnyo/sologate Real-time governance layer for AI agents. Gates fire before risky actions execute.	14	Experimental	—	TypeScript
223	Amayta21/unworldly Record and replay AI agent actions with tamper-proof, ISO 42001-compliant...	14	Experimental	—	—
224	Qwayk/start-here Start here: safe-by-default API tools for AI agents	14	Experimental	—	—
225	MukundaKatta/agentsmith The Agent Smith Problem — Detecting emergent self-preservation and...	14	Experimental	—	Python
226	kitxor/checklist-day Operational ground truth for AI agents	14	Experimental	—	Python
227	Gururaj-GJ/zarelva-agent-risk-engine Fraud risk scoring engine for autonomous AI agents. Detects behavioral...	14	Experimental	—	Python
228	ARE2200/orchard-kit 🌳 Build secure, aligned autonomous AI agents with boundary control, trust...	14	Experimental	—	Python
229	stillcuriouscat/permission-patrol AI-powered security guard for Claude Code permission requests	13	Experimental	2	Python
230	CordiaLabs/LetsPing Behavioral firewall + smart human-in-the-loop for AI agents. Durable wait...	13	Experimental	2	TypeScript
231	rohansx/vibeguard Security Property Graph (SPG) oracle for AI coding agents.	12	Experimental	1	Go
232	luca-bellipanni/Multi-Agent-AI-Security-Pipeline Multi-agent AI security pipeline for GitHub Action. AI agents that think...	12	Experimental	1	Python
233	M-DEV-1/agent-audit-log One-of-a-kind proof-first AI agent	12	Experimental	1	Shell
234	skylark118/data-steward-agent Universal Data Steward Agent for SaaS — production-scale data governance...	12	Experimental	1	—
235	OrchardHarmonics/calyx-protocol The Calyx Protocol: Membrane-based security for autonomous AI agents. Now...	12	Experimental	1	—
236	parthamehta123/safeagent A security-first control plane for autonomous AI code agents: sandboxed...	11	Experimental	—	Python
237	Sunidhi-Sourabh/Data-Guardian-Agent Detect. Advise. Protect. All without compromise.	11	Experimental	—	Python
238	ardamoustafa1/TrustMask An AI-powered system for detecting harmful, toxic, or unsafe content using...	11	Experimental	—	Python
239	Grokipaedia/iba-agentic-security Intent-Bound Authorization (IBA): Cryptographic protocol to prevent Intent...	11	Experimental	—	Python
240	vikasKumar2411/verifiable-agent-ci Verifiable Agent Continuous Integration (VACI): A cryptographic framework...	11	Experimental	—	Python
241	mattlgroff/agent-native-auditor Audit websites for agent-native readiness across llms.txt, agents.json,...	11	Experimental	—	TypeScript
242	f13end/holoXtrace Holochain-based, agent-centric AI audit infrastructure with EU AI Act compliance.	11	Experimental	—	Rust
243	compass-soul/agent-safety-skill Safety toolkit for autonomous AI agents: pre-publish security scanning, git...	11	Experimental	—	Shell
244	saranraj1811/sageos-public Secure Agent Governed Execution OS	11	Experimental	—	—
245	GauravASY/Firewall-SIEM-agent An Agentic security system that integrates with Wazuh SIEM to analyze IPsec...	11	Experimental	—	Python

Comparisons in this category

DashClaw and Aegis (61 vs 43) akios and Aegis (56 vs 43) pydantic-ai-middleware and pydantic-ai-shields (59 vs 58) sovereign-shield and intentshield (59 vs 50)