Security & AI safety

Pentesting & offensive security

Pentesting and offensive security projects carry out offensive security work: probing targets, chaining exploits, and running post-exploitation. PentestGPT drives penetration testing through a language model, while rea pushes reverse engineering from app behavior down to native binaries.

763 agents · most starred first

Top 100 of 763

rea★ 470,836

Reverse engineer anything with agents, from app behavior down to native binaries.

pentagi★ 34,661

Fully autonomous AI Agents system capable of performing complex penetration testing tasks

PentestGPT★ 16,524

Automated Penetration Testing Agentic Framework Powered by Large Language Models

hexstrike-ai★ 13,775

HexStrike AI MCP Agents is an advanced MCP server that lets AI agents (Claude, GPT, Copilot, etc.) autonomously run 150+ cybersecurity tools for automated pentesting, vulnerability discovery, bug bounty automation, and security research. Seamlessly bridge LLMs with real-world offensive security capabilities.

Claude-BugHunter★ 13,335

A Claude Code skill bundle for bug hunting and external red-team work - 82 skills, 15 slash commands, 681 disclosed-report patterns curated across 24 core vulnerability classes, plus enterprise identity + infrastructure attack matrices.

Scanners-Box★ 9,220

The Ultimate Open-Source Security Arsenal for Hackers, Enterprises, and AI Agents——面向极客、企业与 AI 智能体的全域开源网络安全工具矩阵

CyberStrikeAI★ 8,876

The system of action for AI-native cybersecurity—where intent becomes governed execution, evidence becomes operational memory, and every operation improves the next.

Empire★ 7,851

Empire is a PowerShell and Python post-exploitation agent.

T3MP3ST★ 7,088

autonomous red teaming platform; multi-agent offensive-security meta-harness

osmedeus★ 6,662

A Modern Orchestration Engine for Security

Decepticon★ 6,656

Autonomous Hacking Agent for Red Team

Awesome-GPT-Agents★ 6,608

A curated list of GPT agents for cybersecurity

CyberStrikeAI★ 6,388

The system of action for AI-native cybersecurity—where intent becomes governed execution, evidence becomes operational memory, and every operation improves the next.

Agentic-Bug-Hunter★ 6,011

AI-powered bug bounty hunting toolkit that works with or without subscription.

merlin★ 5,635

Merlin is a cross-platform post-exploitation HTTP/2 Command & Control server and agent written in golang.

Decepticon★ 5,480

Autonomous Hacking Agent for Red Team

Cairn★ 5,438

Cairn is a general-purpose AI state-space search engine, validated first on autonomous penetration testing. Sometimes misspelled as Carin.

Agentic-Bug-Hunter★ 4,731

AI-powered bug bounty hunting toolkit that works with or without subscription.

artex-global★ 4,220

Global edition of ARTEX — an LLM multi-agent autonomous penetration-testing framework. English default, switchable to Korean/Chinese/Spanish/Japanese. For authorized, defensive and detection use only. (upstream: Autumn-27/ARTEX, AGPL-3.0)

raptor★ 4,039

Raptor turns Claude Code into a general-purpose AI offensive/defensive security agent. By using Claude.md and creating rules, sub-agents, and skills, and orchestrating security tool usage, we configure the agent for adversarial thinking, and perform research or attack/defense operations.

VulnClaw★ 3,948

基于 AI Agent + MCP 工具链 + 渗透 Skill 编排, 配合大语言模型, 自然语言输入 → 自动完成「信息收集 → 漏洞发现 → 漏洞利用 → 报告生成」全流程。

ctf-skills★ 3,745

Agent skills for solving CTF challenges - web exploitation, binary pwn, crypto, reverse engineering, forensics, OSINT, and more

Gepetto★ 3,490

IDA plugin which queries language models to speed up reverse-engineering

redamon★ 3,455

Open-source, self-hosted AI penetration testing framework: maps your attack surface into a graph, autonomously exploits it from a Kali sandbox with human approval gates, and opens PRs that fix what it finds. MCP both ways: plug in any MCP server as a tool, or drive RedAmon from Claude Code or your o

pentestagent★ 3,315

PentestAgent is an AI agent framework for black-box security testing, supporting bug bounty, red-team, and penetration testing workflows.

Pentest-Swarm-AI★ 3,269

Autonomous penetration testing using a swarm of AI agents. Orchestrates recon, classification, exploitation, and reporting specialists with ReAct reasoning — supports bug bounty, continuous monitoring, and CTF modes. Built with Go and 7+ native security tools.

Awesome-REA★ 3,232

Curated tools, case studies and papers for reverse engineering websites, games, apps, binaries, firmware and protocols. Source-reviewed, English and Chinese.

hack-skills★ 2,674

Helping AI Agent become an awesome practical hacker!

hcaptcha-challenger★ 2,586

🥂 Gracefully face hCaptcha challenge with multimodal large language model.

VulnClaw★ 2,510

基于 AI Agent + MCP 工具链 + 渗透 Skill 编排, 配合大语言模型, 自然语言输入 → 自动完成「信息收集 → 漏洞发现 → 漏洞利用 → 报告生成」全流程。

sapper-v2★ 2,501

The first fruit of the Nüwa tree — an autonomous AI pentest legion (634-team champion, 8h unattended, 1B tokens beat 4.5B). Not just a tool: evolvable by design. Grow your own fruit on the Nüwa Foundation (Create/Language/History).

pentest-ai-agents★ 2,470

Turn Claude Code into your offensive security research assistant. Specialized AI subagents for authorized penetration testing plan engagements, analyze recon, research exploits, build detections, audit STIGs, and write reports.

SILENTTRINITY★ 2,342

An asynchronous, collaborative post-exploitation agent powered by Python and .NET's DLR

AboutSecurity★ 1,946

Everything for pentest. | 渗透测试知识库,以 AI Agent 可执行的格式沉淀安全方法论。

CyberStrike★ 1,889

Open-source AI-augmented offensive security harness. 13+ autonomous agents, 150+ LLM providers, 5,300+ models, 7,600+ Ed25519-signed attack skills, 56+ built-in tools, 176+ MCP tools. MITRE ATT&CK, OWASP WSTG, CIS Benchmarks. Post-exploit: Linux/Windows/macOS/AWS/Azure/K8s/CI-CD. Web UI + Cloudflare Tunnel. Your AI red team.

byp4xx★ 1,863

40X/HTTP bypasser in Go. Features: Verb tampering, headers, #bugbountytips, User-Agents, extensions, default credentials...

emp3r0r★ 1,812

Linux-first multi-operator C2 built to stay quiet and keep working. Self-healing mesh with assisted discovery, in-memory execution with encrypted storage, scriptable agents, cross-platform BOFs, SOCKS5 pivoting, and a modular C agent delivered by a sleep-masking stager.

CyberBattleSim★ 1,772

An experimentation and research platform to investigate the interaction of automated agents in an abstract simulated network environments.

burp-ai-agent★ 1,594

Burp Suite extension that adds built-in MCP tooling, AI-assisted analysis, privacy controls, passive and active scanning and more

pentest-ai★ 1,587

Offensive-security MCP server with 205 wrapped tools, 17 specialist agents, and 60 SPA-aware probes for OWASP Top 10. CLI + MCP, BYO LLM. No API key needed on MCP path.

LitterBox★ 1,582

A self-hosted sandbox for red teams to test payloads against modern detection before deployment. MCP integration lets an LLM agent drive analysis end to end.

pentest-copilot★ 1,568

Pentest Copilot is an AI-powered browser based ethical hacking assistant tool designed to streamline pentesting workflows.

NeuroSploit★ 1,549

NeuroSploit is an advanced, AI-powered penetration testing framework designed to automate and augment various aspects of offensive security operations.

LuaN1aoAgent★ 1,494

LuaN1aoAgent is a fully autonomous AI-driven penetration testing agent powered by graph-based cognitive reasoning.

auto-re-agent★ 1,486

Open-source AI reverse-engineering agent using Ghidra and LLMs to reconstruct and validate C/C++ functions from binaries.

agent★ 1,459

Agentic offensive-security in your terminal

open-reverselab★ 1,383

Open-source AI reverse-engineering workspace with a desktop app, red / blue / both analysis, parallel Goals, a security knowledge base, and MCP tools for Ghidra, Frida, x64dbg and Rizin.

xalgorix★ 1,377

Open-source AI penetration testing agent that exploit-verifies every finding. Autonomous 22-phase pentests of web apps & APIs with CVSS-scored PDF reports. Self-hosted, bring your own LLM, or run fully local with Ollama.

0★ 1,348

The open-source cybersecurity harness. Includes a web interface for code analysis, pentesting, vulnerability research, reverse engineering, verification, and fixing + CLI and MCP for agents.

Dark-Moon★ 1,274

Open-source autonomous AI penetration testing. 50 specialist agents across web, API, cloud, Active Directory, Kubernetes, CI/CD and AI/LLM (OWASP LLM Top 10). Runs on a local LLM behind a Privacy Gateway. Integrates with GitHub, GitLab, Jenkins, VS Code, JetBrains, n8n, Grafana & Splunk.

power-pwn★ 1,247

An offensive/defense security toolset for discovery, recon and ethical assessment of AI Agents

kong★ 1,246

The world's first agentic reverse engineer.

hackGPT★ 1,219

I leverage OpenAI and ChatGPT to do hackerish things

pentest-agents★ 1,214

Bug bounty agent framework for Claude Code, Codex, Gemini, Cursor, Windsurf, Copilot, and OpenClaw — 48 agents, 26 commands, 19 CLI tools, 2 MCP servers, autonomous hunt loops, exploit chain builder.

pentestcode★ 1,204

PentestCode - Multi-agent AI penetration testing system with persistent engagement state, strategic coordination, and parallel autonomous operations.

airecon★ 1,095

AIRecon is an autonomous cybersecurity agent that combines a self-hosted Large Language Model (Ollama) with a Kali Linux Docker sandbox and a Textual TUI. It is designed to automate security assessments, penetration testing, and bug bounty reconnaissance — without any API keys or cloud dependency.

rogue★ 1,076

AI Agent Evaluator & Red Team Platform

Cybermes★ 1,047

Autonomous Offensive Security, Bug Bounty & Red Teaming Agent Framework powered by Hermes Agent, specialized reasoning skills, and multi-model LLM orchestration.

eleven★ 1,010

Agent-first reverse engineering for macOS, Windows and Linux: any ACP agent reads, renames and patches binaries, Android apps and GPU kernels next to you.

cain-agent★ 952

Real-world AI penetration testing engineer for authorized assessments — built-in cloud module covering AWS/Azure/GCP + Aliyun/Tencent/Huawei clouds. Built on Claude Agent SDK

ctf-agent★ 945

Autonomous CTF solver that races multiple AI models in parallel. 1st place BSidesSF 2026.

ReconAIzer★ 903

A Burp Suite extension to add OpenAI (GPT) on Burp and help you with your Bug Bounty recon to discover endpoints, params, URLs, subdomains and more!

manjusaka★ 903

牛屎虾 一款基于AI的远程主机管理工具

Tsec-Hackathon★ 891

腾讯云智能渗透黑客松 Official repository of Tencent Cloud Intelligent Penetration Hackathon. Showcasing top open-source projects of LLM-based autonomous penetration agents, including multi-agent collaboration, automated penetration, AI-driven offensive security, and intelligent attack-defense solutions.

ctf-super-hub★ 857

面向小白用户的 CTF / 逆向 Skills 整合包:自动分流、头脑风暴、教学模式、比赛模式、只提示模式

numasec★ 845

The AI Agent for Cyber Security.

KaliGPT★ 812

KaliGPT: an Agentic AI (built with Gemini, ChatGPT, Ollama, OpenRouter Models) fine tuned for ethical hackers & students in offensive security making workflows smarter, faster, and more accessible.

MCP-Kali-Server★ 701

MCP configuration to connect AI agent to a Linux machine.

xalgorix★ 693

Xalgorix - Autonomous AI Pentesting Agents

communitytools★ 630

Open-source Claude Code skills, agents, and slash commands for AI-powered penetration testing, bug bounty hunting, and security research

agent-opfor★ 587

Open-source adversary emulation for AI agents and MCP servers.

mcp-reverse★ 573

MCP (Model Context Protocol) server for game hacking & reverse engineering. A structured knowledge base of 4,100+ skills with full source code archives, specialized agents, and workflow tools -- designed to be plugged into Claude, Cursor, or any MCP-compatible client.

LockKnife★ 565

LockKnife: The Ultimate Android Security Research Tool. A unified TUI workspace and headless CLI for deep Android security research, built for researchers and hackers. Powered by Python orchestration and a Rust-accelerated core, enabling AI agent–driven hacking, credential recovery/cracking, APK analysis, intelligence gathering, runtime inspection.

ARTEMIS★ 552
Cyber-AutoAgent★ 551

AI agent for autonomous cyber operations

hackagent★ 540

HackAgent is an open-source security toolkit to detect vulnerabilities of your AI Agents

EVA★ 534

EVA is an AI-assisted penetration testing agent that enhances offensive security workflows by providing structured attack guidance, contextual analysis, and multi-backend AI integration.

BananaPhone★ 532

It's a go variant of Hells gate! (directly calling windows kernel functions, but from Go!)

cybersecurity-skills★ 526

Cybersecurity skills for AI coding agents (Claude Code, Cursor, Codex)

AIDA★ 517

Turn any LLM into an autonomous pentester. You define the scope, the agent does the work, you review the findings.

muteki★ 514

Project Muteki (無敵): autonomous multi-model CTF-solving AI agent swarm

Zen-Ai-Pentest★ 511

🛡⚔️AI-Powered Penetration Testing Framework with automated vulnerability scanning, multi-agent system, and compliance reporting🛡⚔️

mantishack★ 508

Mantis Hack

bugbounty-lab101★ 497

A complete bug bounty workspace for HackerOne researchers. Includes scope enforcement, automated recon/vuln pipeline (400+ tools), report templates, CVE/CWE watchlists, and a local VM practice lab. Built for disciplined, ethical hunting.

Awesome-Offensive-AI-Agentic-Landscape★ 495

This document curates open-source projects, academic papers, capability benchmarks, and commercial solutions (international & China) in AI penetration testing, LLM red teaming, autonomous offensive agents, and vulnerability discovery—aimed at helping researchers, security engineers, and enterprise decision-makers quickly form a holistic view.

BreachWeave★ 494

智能渗透Agent Manager/Observer/Solver 多角色架构,基于 pi-mono SDK。

Z3r0★ 491

AI-native red-team workbench for authorized penetration testing and vulnerability research, with specialist agents, sandboxed tooling, evidence records, and replayable timelines.

re-shell★ 489

Nix-powered agentic reverse engineering environment

rogue★ 483

Automated web vulnerability scanning with LLM agents

pentest-harness★ 476

Pentest Harness — Heaven for Hackers. A self-hosted AI agent harness for authorized pentests, bug bounty, security labs, and CTFs. Bring your own AI model API; sessions stay local.

Full-Chain-Sentinel-System★ 473

【全链哨兵】全流程渗透测试 Agent 系统,支持 Web、小程序、安卓 APP、IOS app(测试中)。安全服务渗透测试辅助工具,禁止用于非法攻击。

BoxPwnr★ 471

A modular framework for benchmarking LLMs and agentic strategies on security challenges across HackTheBox, TryHackMe, PortSwigger Labs, Cybench, picoCTF and more.

Bug-Bounty-Agents★ 471

AI-Powered Agents for Bub-Bounty Pentesting and Red-Teaming purposes

AiScan-N★ 465

AiScan-N 来了!这是一款基于人工智能驱动的Ai自动化网络安全(运维)工具,专注于网络安全评估、漏洞扫描、运维、应急响应、渗透测试自动化,Ai大模型工具集【CLI Agent】 ,Ai驱动的安全检测技术,提升安全测试(运维)效率,专为企业和个人用户打造,尤其适合初学者(小白)快速上手使用,让你轻松迈入智能安全攻防时代!适用场景 :如(红队演练、CTF比赛、Web应用渗透测试、内网横向移动、密码破解与暴力攻击、流量分析与威胁检测、APT攻击模拟、漏洞赏金挑战等场景)🎥演示视频(文章中):https://mp.weixin.qq.com/s/7lsUdbrxkDy4P5pZhEWv7Q

bountyforge★ 464

all round pentest skill

AgentHound★ 464

Offensive security framework for AI agent infrastructure - recon, credential looting, model exfiltration, poisoning, and attack-path analysis across MCP, A2A, gateways, and AI services. BloodHound for the agentic stack.

exploitbench★ 452

ExploitBench measures how far AI agents climb, from reaching vulnerable code, to triggering the bug, to building exploit primitives, to arbitrary code execution.

cyber-harness★ 430

AI-driven pi-like agent for cyber security — single binary for pentest, red team, bug bounty

Pojun★ 422

AI 自主渗透测试 · 红队作战平台 | 多 Agent 自主推进 · 漏洞情报运营 · 后渗透与 C2 | LLM 三通道轮询 | 全程证据留痕 | 原百度攻防赛冠军项目独立演进版

superclaw★ 416

SuperClaw: Red-Team AI Agents Before They Red-Team You

More in Security & AI safety