Havuz

Run cyber-AI agents against real missions in isolated environments. Record everything as OpenTelemetry evidence. Grade the evidence, not the

🥷 Give your codebase a black belt. Local code intelligence, security analysis, and compiler-backed facts for humans and AI.

Install, run and verify OSINT tools from GitHub automatically, on any OS

Agentic memory for CTI in Python — STIX knowledge graphs, threat-actor alias resolution, offline-first RAG, MCP server for Claude Code and L

High-fidelity Claude Fable 5 (Mythos) environment emulation and automated multi-agent jailbreak (Pack Hunt) research laboratory.

Open-source asset inventory — turn scattered, contradictory tool data into one reliable inventory, then chat with it using the LLM of your c

🛡️ A modern, AI-powered WAF with visual forensic playback via rrweb. Protect your web apps with LLM-driven threat detection, real-time visua

Open-source benchmark of 5 intentionally vulnerable web apps with 100 baseline vulnerabilities for evaluating AI penetration testing agents.

Dark-GPT: The ultimate unrestricted AI assistant for cybersecurity research by M4TH4CK3R

Elevate your AI assistants (like Claude & Cursor) into autonomous cybersecurity experts. Pentester-MCP integrates 200+ pentesting tools via

AI agent browser for web reverse engineering

Get Claude Code and other AI agents approved for use at work — deterministic guardrails on every tool call, tamper-evident audit logs, and a

🛡️ Turnkey cybersecurity lab for Hermes Agent — 397 CVE-driven skills, 152 tools, 28 frameworks (MITRE ATT&CK, MISP, CVSS, EPSS, OWASP, NIST

Outside-in replication of Anthropic's Mythos Preview / Project Glasswing — open-source agentic vulnerability-discovery scaffold on Claude Op

The AI security agent guards your code.

AI Firewall & LLM security toolkit - protect your AI applications from prompt injection, jailbreaks, PII leakage, and adversarial attacks

Detonate files & URLs in cloud malware sandboxes (Hybrid Analysis, tria.ge, ANY.RUN) and enrich IOCs across MalwareBazaar, ThreatFox, URLhau

Declaratively deploy & manage multiple isolated AI agents on a single NixOS machine — each with its own secrets, skills, and personality.

TriLane: autonomous AI pentester and multi-agent security auditor for authorized gray-box testing of web apps and APIs. Built with Rust and

Rust-native, multi-session headless IDA Pro MCP server with isolated workers and stdio or Streamable HTTP transports.

Verifiable and free cloud compute for AI agents. webMCP + MCP native. Check out our sandboxed Beta + research in the README

Self-hosted AI-assisted CTI-to-detection workbench for ATT&CK mapping, IOC/CVE intelligence, Threat Radar, malware triage, Attack Simulation

LingXi: multi-agent CTF and pentest framework originated from Tencent Security Hackathon

An OWASP-aligned intentionally vulnerable platform for learning and testing AI, LLM, RAG, MCP, and Agentic AI security.

AI Agent + 抓包融合安全测试工具 | 自然语言驱动自主渗透测试 | ReAct 编排引擎 | Tauri + FastAPI

The autonomous pentester that proves its findings — AI-driven, evidence-first, behind-login.

LLM-first deception framework: "The honeypot that talks back!™"

Cyber Threat Intelligence Skills for each stage of the CTI Lifecycle.

MCP server with 55 security intelligence tools — CVE/KEV, MITRE ATLAS+D3FEND, Sigma detection rules, email security posture (SPF/DMARC), dom

Empowers the AI to perform penetration testing, vulnerability assessment, reconnaissance, and security reporting — all through natural langu

Cybersecurity knowledge graph for code review with evidence-backed answers

bb-huge 🤗 , Personal bug bounty findings hub and bug bounty orchestration for multiple agents

LLM benchmark results for THOR forensic finding triage quality

Self-hosted, agentic vulnerability research for binaries & firmware: an AI agent decompiles, fuzzes, and verifies exploits inside a sandbox,

AI Powered Reverse Engineering Tool

An autonomous agentic pipeline that finds, proves, and patches real C memory-safety vulnerabilities end-to-end using a single 7B open-source

AI-orchestrated, Kali-native pentesting lab: an MCP tool-server with scope/VPN/rate/audit enforced in code, independent finding verification

Red Team + Blue Team agents for Claude Code. Automated security auditing with ~100 lines of Markdown each.

ThreatRadar is an open-source Threat Intelligence pipeline for SOC and threat intelligence teams that ingests, enriches, scores, and validat

AI-powered log diagnostics engine that analyzes server logs, stack traces, and infrastructure failures to identify root causes and recommend

Static security scanner for AI agent skill packages. Detects malicious SKILL.md files and bundled scripts before they run.

An elite, self-orchestrating cyber-offensive platform built for relentless surface expansion, real-time intelligence gathering, precision vu

FRIDAY is an autonomous cognitive AI operating system for memory, reasoning, voice, cybersecurity, and self-improvement. It runs locally and

A privacy-first, fail-closed AI pentest conductor and autonomous Red Team platform

Talk to your computer. Icebreaker transforms natural language into safe Linux actions through isolated AI brains, kernel-enforced sandboxes.

Official VulnCheck MCP Server

Open-source config scanner for AI coding agents: scores the permissions, hooks, sandbox and MCP settings of Claude Code, Codex, Cursor and G

Harness-driven terminal AI agent for authorized security assessment, with TUI, headless automation, persistent context, 150 built-in skill

Autonomous web-app pentest engine — a multi-agent pipeline wielding 30+ offensive-security tools as skills, PoC-validated findings. Built on