Uncategorized AI Safety Tools

There are 102 uncategorized tools tracked. 5 score above 70 (verified tier). The highest-rated is BlackArch/blackarch at 76/100 with 3,312 stars. 5 of the top 10 are actively maintained.

Get all 102 projects as JSON

curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=ai-safety&subcategory=uncategorized&limit=20"

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

#	Tool	Score	Tier	Stars	Language
1	BlackArch/blackarch An ArchLinux based distribution for penetration testers and security researchers.	76	Verified	3,312	Shell
2	BishopFox/sliver Adversary Emulation Framework	73	Verified	10,982	Go
3	casdoor/casdoor An open-source AI-first Identity and Access Management (IAM) /AI MCP & agent...	72	Verified	13,323	Go
4	0xsyr0/Awesome-Cybersecurity-Handbooks A huge chunk of my personal notes since I started playing CTFs and working...	71	Verified	3,361	—
5	openguardrails/openguardrails Protect every action your agent takes.	70	Verified	332	TypeScript
6	Agent-Threat-Rule/agent-threat-rules Open detection standard for AI agent threats. Like Sigma, but for prompt...	68	Established	90	TypeScript
7	zan8in/afrog A Security Tool for Bug Bounty, Pentest and Red Teaming.	67	Established	4,232	Go
8	globalbao/awesome-azure-policy A curated list of blogs, videos, tutorials, code, tools, scripts, and...	63	Established	537	—
9	Pantheon-Security/medusa AI-first security scanner with 76 analyzers, 9,600+ detection rules, and...	55	Established	251	Python
10	dapurv5/awesome-red-teaming-llms Papers from our SoK on Red-Teaming (Accepted at TMLR)	54	Established	42	—
11	IBM/ares AI Robustness Evaluation System	54	Established	38	Python
12	The-Z-Labs/bof-launcher bof-launcher - a library for loading, executing and in-memory masking BOFs...	54	Established	307	Zig
13	H3llKa1ser/B00t2R00t A penetration testing Swiss Army Knife that's suitable for CTF challenges,...	53	Established	33	Python
14	aisa-group/PostTrainBench Measuring how well CLI agents like Claude Code or Codex CLI can post-train...	51	Established	259	Python
15	emmanuelgjr/GenAI-Security-Crosswalk The most comprehensive open-source mapping of OWASP GenAI risks to industry...	50	Established	6	JavaScript
16	microsoft/llmail-inject-challenge Code for the API, workload execution, and agents underlying the...	49	Emerging	23	Python
17	microsoft/Test_Awareness_Steering Code for the paper: Linear Control of Test Awareness Reveals Differential...	49	Emerging	11	Jupyter Notebook
18	mensfeld/code-on-incus Run coding agents in hardened Incus containers with real-time network threat...	49	Emerging	379	Python
19	skoveit/skovenet Decentralized Adversary Emulation Framework	49	Emerging	27	Go
20	Shiritai/sanity-gravity Providing a strong Gravity in the wild world of Antigravity (AI Agents), to...	48	Emerging	23	Python
21	bm-github/owasp-social-osint-agent AI-powered OSINT framework for multi-platform social media intelligence...	48	Emerging	62	Python
22	knostic/openclaw-shield Security plugin for OpenClaw agents - prevents secret leaks, PII exposure,...	47	Emerging	70	TypeScript
23	davidmatousek/tachi Automated threat modeling toolkit — STRIDE + AI-specific threats in one command	45	Emerging	29	Python
24	ProfessionalWiki/PageApprovals Increase trust in your wiki knowledge base via approval workflows	45	Emerging	2	PHP
25	s-r-e-e-r-a-j/GhostBuilder GhostBuilder is a powerful payload generator tool designed for ethical...	44	Emerging	20	Python
26	romovpa/claudini Autoresearch for LLM adversarial attacks	44	Emerging	182	Python
27	GnomeMan4201/zer0DAYSlater Instrumented adversarial simulation framework for studying detection,...	44	Emerging	3	Python
28	nikthink/pauseai.ca https://pauseai.ca/	43	Emerging	4	JavaScript
29	Ruso-0/Nreki MCP plugin that intercepts AI agent edits in RAM, validates them ...	43	Emerging	2	TypeScript
30	HASHIRU-AI/NAAMSE Neural Adversarial Agent Mutation-based Security Evaluator	42	Emerging	15	Python
31	Fan1234-1/tonesoul52 AI governance framework — semantic responsibility, self-auditing memory,...	42	Emerging	5	Python
32	rehydra-ai/rehydra-sdk Prevent accidental PII leakage in LLM prompts before they hit the model.	42	Emerging	61	TypeScript
33	StackOneHQ/defender Open source prompt injection protection for Agents calling tools (via MCP,...	41	Emerging	80	TypeScript
34	t81dev/t81-foundation T81 is the first operating system built for governed, deterministic AI...	41	Emerging	2	C++
35	aegis-initiative/aegis-governance [.com] Architectural governance framework for AI systems enabling...	41	Emerging	4	JavaScript
36	FIND-Lab/AgentWard AgentWard – Built for all, hardened for OpenClaw.	41	Emerging	30	TypeScript
37	Tooooa/AgentMark 【ACL 2026 Main】AgentMark: Utility-Preserving Behavioral Watermarking for Agents	41	Emerging	76	Python
38	trnt-ai/trent-openclaw-security-assessment Free security assessment for your OpenClaw 🦞 environment. Scans gateway...	40	Emerging	5	Python
39	ppcvote/prompt-defense-audit Deterministic LLM prompt defense scanner — 12 attack vectors, pure regex,...	40	Emerging	3	TypeScript
40	HOLYKEYZ/IntellectSafe AI defense infrastructure against manipulation, misuse, hallucinations, and...	40	Emerging	20	Python
41	gd2bk1ng/syntra_kernel Syntra Kernel is a Cognitive Operating System - A modular,...	39	Emerging	4	Rust
42	readme-SVG/Issues-heroes-badge Serverless Vercel API that renders an animated SVG badge from validated...	39	Emerging	5	Python
43	AbdelStark/awesome-ai-safety A curated list of AI safety resources: alignment, interpretability,...	39	Emerging	22	—
44	sane-apps/SaneProcess Workflow enforcement for coding agents: Claude Code hooks, Codex...	38	Emerging	8	Ruby
45	bitflight-devops/hallucination-detector Zero-dependency Claude Code plugin that catches speculation, invented...	38	Emerging	6	JavaScript
46	Myth727/ARCHITECT-Universal-Coherence-Engine Full-stack inference-time coherence engine for LLM conversations. Per-turn...	38	Emerging	5	JavaScript
47	bkr1297-RIO/rio-receipt-protocol RIO Receipt Protocol — Cryptographic proof for AI actions. Open standard for...	38	Emerging	2	JavaScript
48	ansonsaju/project-claudia Meet Claudia: An adversarial AI agent for Project Sentinel that relentlessly...	38	Emerging	2	JavaScript
49	NeuZhou/agentimmune The first firewall for AI agents. Stops prompt injection, data leaks, and...	37	Emerging	3	TypeScript
50	Diplomat-ai/diplomat-agent AI agent scanner to finds every tool call that can change the real world and...	37	Emerging	3	Python
51	fairvisor/edge Open-source edge engine to control API request budgets and enforce fair usage.	36	Emerging	8	Lua
52	renefichtmueller/ShieldX Self-Evolving LLM Prompt Injection Defense — 547+ rules, 50+ languages,...	36	Emerging	6	TypeScript
53	RafaelParonis/jailbench 🔍 Benchmark jailbreak resilience in LLMs with JailBench for clear insights...	36	Emerging	3	Python
54	nhowardtli/virp VIRP Protocol: Cryptographic Trust Primitives and Network Trust Anchor...	36	Emerging	8	C
55	efij/secure-claude-code Security guardrails for Claude Code, MCP tools, and Claude cowork workflows....	34	Emerging	87	Python
56	kureha-yamaguchi/reasoning-manipulation Adversarial Manipulation of CoT	33	Emerging	8	Jupyter Notebook
57	Nicholas-Kloster/claude-4.6-jailbreak-vulnerability-disclosure-unredacted Three Claude production tiers generated functional exploit code against live...	33	Emerging	26	HTML
58	minggo-commits/prompt-labs The definitive open-source guide for mastering AI Prompt Engineering techniques.	33	Emerging	3	TypeScript
59	dapurv5/alignmark Watermarking Degrades Alignment in Language Models: Analysis and Mitigation...	32	Emerging	4	Python
60	alivsch-ai-code/flux-bot-azamat Python Telegram Bot für AI-Bild- und Video-Generierung. Replicate API, Neon...	32	Emerging	2	Python
61	ParraX123/meta-ai-bug-bounty 🛡️ Discover and analyze critical vulnerabilities in Meta AI's Instagram...	31	Emerging	3	—
62	Jonathanmutu/recursive-containment-framework A recursive alignment framework for cognitive coherence, belief tracking,...	31	Emerging	2	—
63	teilomillet/enzu Budgeted LLM runs with hard caps + typed outcomes + async job mode....	31	Emerging	2	Python
64	AionSystem/AION-BRAIN The left hemisphere. Frameworks, logic, and certainty architecture. Home of...	31	Emerging	11	Python
65	Convergence-Human-And-Technology/sovereign-drive R&D · Legally accountable AI systems for autonomous vehicle operation...	30	Emerging	5	—
66	alyssadata/Emergent-Agency DEMO-READY Automated consistency verification for behavioral tracking....	29	Experimental	3	—
67	Dandona100/SafeEyes │ Real-time NSFW & harmful content detection as a service	29	Experimental	3	Python
68	Project-Navi/navi-creative-determinant The Creative Determinant: autopoietic closure as a nonlinear elliptic BVP on...	29	Experimental	3	TeX
69	aisa-group/skill-inject Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks	29	Experimental	48	Python
70	Lukentony/AI-guardian-lab Security middleware for AI Agents. Intercepts shell commands before...	28	Experimental	7	Python
71	LogicPearlHQ/logicpearl Your logic, distilled into pearls. ⚪	28	Experimental	3	Rust
72	thansz137/asiyah-protocol A philosophical approach for synthetic minds. An open door, an extended...	28	Experimental	2	—
73	URDev4ever/LATT LLM Attack Testing Toolkit is a structured methodology and mindset framework...	28	Experimental	5	—
74	Mindburn-Labs/helm-oss HELM OSS — Open-source core of the HELM Autonomous OS. Policy enforcement,...	28	Experimental	5	Go
75	yunbeizhang/MM-Plan [ICLRW 2026 Oral] Visual Exclusivity Attacks: Automatic Multimodal Red...	27	Experimental	4	Python
76	HUNT-001/ai-chip-design-platform Multi-agent RISC-V verification and test-generation framework for...	27	Experimental	4	Python
77	atani/mysh MySQL connection manager with SSH tunnel support. Auto-masks sensitive data...	27	Experimental	3	Go
78	souvikghosh957/secret-sanitizer-extension Chrome extension that masks secrets & sensitive data before pasting into AI...	27	Experimental	4	JavaScript
79	Jang-woo-AnnaSoft/execution-boundaries Design notes on execution boundaries and responsibility structures for AI...	27	Experimental	3	—
80	hiranp/hief HIEF (Hybrid Intent-Evaluation Framework) Persistent Memory Layer for AI...	27	Experimental	3	Rust
81	nhomyk/agenticqa-scan-action Map every integration point in your AI codebase — 13 CWE categories, attack...	26	Experimental	2	Python
82	EntropyWizardchaos/developmental-ai-governance Developmental lifecycle architecture for AI agents: childhood stages,...	26	Experimental	2	Python
83	Kibertum/SENAR SENAR — Supervised Engineering & Normative AI Regulation. Open methodology...	26	Experimental	5	Astro
84	Ratila1/JGuardrails 🛡️ Programmable Guardrails for LLM Applications in Java. A...	26	Experimental	7	Java
85	yurukusa/cc-safe-setup One command to make Claude Code safe for autonomous operation. 658 example...	26	Experimental	8	Shell
86	nevitonsantana/aletheia Operating framework for AI-assisted work with decision, governance,...	25	Experimental	3	TypeScript
87	kiyoshisasano/agent-failure-debugger A deterministic pipeline that diagnoses, explains, and safely auto-fixes...	25	Experimental	3	Python
88	0xadvait/divergence-explorer Autonomous AI researcher that probes where frontier models disagree — with...	25	Experimental	4	Python
89	prompt-armor/prompt-armor Open-source prompt injection detector — 5 layers, 91.7% F1, ~27ms, offline,...	25	Experimental	3	Python
90	AKURHULA/LLMSecurityGuide 🛡️ Explore tools for securing Large Language Models, uncovering their...	24	Experimental	3	—
91	dstours/OctoC2 GitHub-native Command & Control Framework. 11 covert channels. Zero infrastructure.	24	Experimental	2	TypeScript
92	solanticai/vibe-guard AI coding guardrails framework. Runtime-enforced quality controls for Claude...	24	Experimental	2	TypeScript
93	dislovelhl/acgs-lite Constitutional governance infrastructure for AI agents — the missing safety...	24	Experimental	2	Python
94	michaelgregoryibizugbe/PHANTOM-RECON 👻 PHANTOM-RECON Is An Advanced Network Reconnaissance Tool With...	24	Experimental	2	Python
95	sushaan-k/infiltr RL-based LLM red-team framework with MITRE ATLAS reporting and CI-ready outputs	24	Experimental	2	Python
96	velzepooz/skill-detector CLI to spot risky AI skill packages before you use them. Scans for...	24	Experimental	2	Go
97	anthril/vibe-guard AI coding guardrails framework. Runtime-enforced quality controls for Claude...	24	Experimental	2	TypeScript
98	gw0/docker-claude-code Dockerized Claude Code Sandbox	21	Experimental	3	Dockerfile
99	safal207/Living-Relational-Identity-LRI Living Relational Identity (LRI) defines non-operational invariants that...	20	Experimental	2	Python
100	zscaler/zguard-ai-integrations Central documentation repository for all integrations with Zscaler AI Guard	18	Experimental	2	Python
101	Orellius-Archive/orellius-cognitive ⚠️ UNMAINTAINED — AI personality, safety, red-teaming, and sandboxing in Rust SDK.	16	Experimental	9	Rust
102	imurtuja/InkVerse Where Code Meets Poetry 🪶 A premium, production-grade social ecosystem for...	16	Experimental	2	JavaScript