AI Security Training Labs LLM Tools

Hands-on learning environments, CTF challenges, and vulnerable-by-design systems for practicing AI/LLM security skills. Includes red teaming exercises, cyber ranges, and interactive labs. Does NOT include general security resources, compliance frameworks, or production defense tools.

There are 56 ai security training labs tools tracked. 2 score above 50 (established tier). The highest-rated is KryptSec/oasis at 52/100 with 16 stars.

Get all 56 projects as JSON

curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=llm-tools&subcategory=ai-security-training-labs&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	KryptSec/oasis Open-source AI security benchmarking CLI. Measure how AI models perform...	52	Established	16	TypeScript
2	bobby-tablez/TTP-Threat-Feeds Threat feeds designed to extract adversarial TTPs and IOCs, using: ✨AI✨	50	Established	70	Python
3	depalmar/ai_for_the_win Build AI-powered security tools. 50+ hands-on labs covering ML, LLMs, RAG,...	48	Emerging	125	Python
4	format81/TI-Mindmap-GPT AI-powered tool designed to help producing Threat Intelligence Mindmap.	48	Emerging	106	Python
5	ethiack/ai4eh AI for Ethical Hacking - Workshop	46	Emerging	278	Python
6	hupe1980/aisploit 🤖🛡️🔍🔒🔑 Tiny package designed to support red teams and penetration testers in...	45	Emerging	26	Python
7	AISecurityConsortium/AIGoat AI Goat - Learn AI security by attacking and defending a real AI-powered...	44	Emerging	25	JavaScript
8	amazon-science/Cyber-Zero Cyber-Zero: Training Cybersecurity Agents Without Runtime	44	Emerging	77	Python
9	aira-security/Vulnerable-AI-Chatbot An intentionally vulnerable AI chatbot to learn and practice AI Security.	39	Emerging	16	HTML
10	dhammon/ai-goat Learn AI security through a series of vulnerable LLM CTF challenges. No sign...	38	Emerging	325	Python
11	yevh/TaaC-AI AI-driven Threat modeling-as-a-Code (TaaC-AI)	38	Emerging	161	HTML
12	AINTRUST-AI/aixploit Engineered to help red teams and penetration testers exploit large language...	37	Emerging	8	Python
13	cyberviser/Hancock 🛡️ Hancock — AI-powered cybersecurity agent for pentesting, SOC analysis &...	37	Emerging	2	Jupyter Notebook
14	elementsinteractive/lightman-ai LLM-powered cybersecurity news aggregator	37	Emerging	3	Python
15	alexdevassy/Machine_Learning_CTF_Challenges CTF challenges designed and implemented in machine learning applications	35	Emerging	207	HTML
16	fearmotor/genai-security-training 🔴 Elevate your security skills with hands-on training in red teaming for...	35	Emerging	1	Jupyter Notebook
17	taoq-ai/ziran ZIRAN is an open-source security testing framework for AI agents. It...	33	Emerging	2	Python
18	NVISOsecurity/cyber-security-llm-agents A collection of agents that use Large Language Models (LLMs) to perform...	33	Emerging	257	Jupyter Notebook
19	thisistanishq/chronos Neural Asset Intelligence System modeling adversarial credential extraction...	32	Emerging	1	Python
20	ZySec-AI/project-zysec The project serves as a strategic advisory tool, capitalizing on the ZySec...	32	Emerging	68	Python
21	uebelack/bug-bounty-hunting-ai Demo code and presentation materials for the talk "Bug Bounty Hunting with...	32	Emerging	6	Python
22	mbrg/genai-attacks A knowledge source about TTPs used to target GenAI-based systems, copilots and agents	30	Emerging	139	Python
23	xvnpw/ai-threat-modeling AI featured threat modeling and security review project	30	Emerging	17	Python
24	byt3n33dl3/CXCPenX-Az Infra based AzureAD adversarial emulation kit, deliver attack telemetry and...	28	Experimental	1	Go
25	PurCL/ASTRA 🥇 Amazon Nova AI Challenge Winner - ASTRA emerged victorious as the top...	28	Experimental	70	Python
26	regaan/basilisk Basilisk — Open-source AI red teaming framework with genetic prompt...	26	Experimental	7	Python
27	clolomagico123/ai-security-lab 🤖 Test and secure AI systems with advanced techniques for Large Language...	25	Experimental	3	—
28	DevOpsMadDog/Fixops ALdeci — AI-powered Decision Intelligence for Security Teams. Multi-LLM...	25	Experimental	4	Python
29	xvnpw/ai-nutrition-pro-design-gpt4 Research project on AI usage for threat modeling and security review and...	25	Experimental	4	—
30	ibndias/CIPHER Cybersecurity Intelligent Pentesting Helper for Ethical Researcher (CIPHER)....	25	Experimental	37	Python
31	three2hot/cyber-agent 🤖 Automate penetration testing with AI using Cyber Agent, powered by Claude...	23	Experimental	1	—
32	xvnpw/ai-nutrition-pro-design-claude2 Research project on AI usage for threat modeling and security review and...	22	Experimental	7	—
33	Panda1847/ai-security-lab 🤖 Advanced AI/LLM Security Testing Framework. Includes 50+ jailbreak...	22	Experimental	3	—
34	naflashDev/CyberMind Plataforma modular de ciberseguridad IT/OT con IA, scraping, dashboards y...	22	Experimental	—	Python
35	kneha10/cyber-forge 🛡️ Simulate breach probabilities and visualize cybersecurity risk with...	22	Experimental	—	HTML
36	Samuel411-mbiri/Hancock Automate cybersecurity tasks using specialized large language models for...	22	Experimental	—	Jupyter Notebook
37	ayushgayakwad/RAIDER RAIDER is an autonomous AI Red Teaming system that combines Reinforcement...	22	Experimental	3	Python
38	SuchetSanjeev/EncryptedTrafficAttackClassifierLLMs This cybersecurity classifier integrates a lightweight LLM with a Random...	20	Experimental	1	Python
39	skyvanguard/security-agent-cookbook Practical recipes and templates for building cybersecurity AI agents with...	19	Experimental	—	Python
40	0PeterAdel/CyberBrain_Model CyberBrain_Model is an advanced AI project designed for fine-tuning the...	19	Experimental	22	Jupyter Notebook
41	alihassanassi/ORYN Local-first autonomous cybersecurity console. Dual-model LLM, 7-gate safety...	18	Experimental	6	Python
42	WHAZAZA/AI-cyber-range ⚔️ Build, break, and secure Large Language Models with our automated OWASP...	16	Experimental	2	Python
43	shreeramdrao/Cysinfo-AI Cysinfo AI is a project utilizing Large Language Models (LLMs) and...	16	Experimental	1	Vue
44	JuanCho829/Awesome-AI-Deception 🍯 Discover AI-driven deception resources, including honeypots, datasets, and...	15	Experimental	1	—
45	sehgalrishabh/fortifai-cli FortifAI CLI is a black-box adversarial testing tool for production AI...	14	Experimental	—	TypeScript
46	nwejnkasdf/TRAITHON_GPS.dev TRAITHON - Trustworthy AI Marathon Contribution	14	Experimental	—	Jupyter Notebook
47	heyyatheworld/bug-hunter 🤖 BugHunter — An educational project showcasing LLM capabilities in...	14	Experimental	—	Python
48	VolkanSah/Implementing-AI-Systems-Whitepaper This whitepaper provides best practices and concrete examples for the secure...	13	Experimental	10	—
49	hongyingyue/CyberLLM Cybersecurity LLM	13	Experimental	2	Python
50	usrtem/AI-Cybersecurity-Research White-paper & talk covering benefits, risks, and mitigation frameworks for...	12	Experimental	1	—
51	urcuqui/orion Orion is an AI security framework, inspired by The Art of War, for red and...	12	Experimental	1	Jupyter Notebook
52	xvnpw/ai-nutrition-pro-design-gpt3.5 Research project on AI usage for threat modeling and security review and...	11	Experimental	2	—
53	0xguardstate/cyber-security-llm-agents A collection of agents that use Large Language Models (LLMs) to perform...	11	Experimental	—	Jupyter Notebook
54	diorwave/Cyber-Security-LLM-Agents A collection of agents that use Large Language Models (LLMs) to perform...	11	Experimental	7	Jupyter Notebook
55	vicenteaguero/llmalware Focused on LLM-driven obfuscation and deobfuscation: This project leverages...	11	Experimental	2	Python
56	mcxiaoxiao/CyberDefense-LLM 事件关联分析与机器学习解决告警降噪的问题学习材料+调研笔记+数据集	11	Experimental	2	—

Comparisons in this category

AIGoat and ai-goat (44 vs 38) aisploit and aixploit (45 vs 37)