Skip to content

Entry

PentestGPT

Appears in 6 awesome lists

🟢🔬 — The original USENIX'24 LLM pentest agent; re-released as an autonomous pipeline with strong benchmark results. · updated 2026-07-14)

Open github.comgreydgl/pentestgpt

Found in these lists

Awesome Ai Agents 2026

Section: Cybersecurity Agents · GPT-powered pentesting. Automated reasoning.

ActiveScore 70

Awesome AI Security Tools

Section: Pentest & Red-Team Agents · 🟢🔬 — The original USENIX'24 LLM pentest agent; re-released as an autonomous pipeline with strong benchmark results. · updated 2026-07-14)

FreshScore 91

Awesome Bug Bounty Tools

Section: AI Agents · AI-powered penetration testing assistant that helps automate security testing workflows and vulnerability discovery.

FreshScore 93

awesome-ChatGPT-repositories

Section: NLP · A GPT-empowered penetration testing tool

FreshScore 87

awesome-python

Section: Security Tools · Automated Penetration Testing Agentic Framework Powered by Large Language Models

FreshScore 79

Awesome AI Agents: Tools, Resources, and Projects

Section: Tools · A GPT-empowered penetration testing tool

SlowScore 66

Darkmoon

🟢⚠️ — Autonomous AI penetration-testing platform that orchestrates specialized web, AD, Kubernetes, CMS, and framework agents through an MCP-controlled Docker toolbox with local privacy-tokenization for sensitive target data. — note: GPL-3.0 licensed; heavy Docker/LLM stack, use only for…;…

In 11 listsDetails

RedAmon

🟢⚠️ — Self-hosted AI pentest framework combining reconnaissance, a Neo4j attack-surface graph, Kali-based tooling, configurable human approvals, and agent-assisted remediation pull requests, with MCP client and server interfaces. — note: authorized testing only, on a dedicated isolated host. The…

In 5 listsDetails

PentAGI

Fully autonomous AI agent system for conducting ethical hacking and complex penetration testing tasks. MIT licensed.

In 5 listsDetails

CAI

🟢🟠🔬⚠️ — Archived modular agent framework for model-assisted offensive and defensive security workflows, retained as a research reference. (Alias Robotics) Caveat: no further releases or security fixes are planned. The current archive combines MIT upstream components with Alias Robotics…

In 4 lists

T3MP3ST

Multi-agent offensive-security meta-harness (July 2026) that turns the coding agent you already run — Claude Code, Codex, OpenCode, or a fully offline Ollama/vLLM model — into an autonomous kill-chain hunter (recon → exploit → report) across web apps, CTFs, smart contracts, and source code. The…

In 3 lists

Burp Suite MCP Server

PortSwigger's Burp Suite extension serves an MCP endpoint, plus a packaged stdio proxy, so agents can query proxy HTTP and WebSocket history, send HTTP/1.1 or HTTP/2 requests, and open Repeater or Intruder tabs. Integration · Independent MCP · Also: App · Full entry

In 3 lists

HexStrike-AI

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…

In 3 lists

Strix

Autonomous AI-powered penetration testing agent that identifies vulnerabilities and validates them with proof-of-concept exploits. Apache 2.0 licensed.

In 3 lists