GreyDGL/PentestGPT

Health v2 · maintenance only

Adoption not part of the score

15091 stars · 2632 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

PentestGPT is an AI-powered penetration testing agent framework that drives LLMs (Claude Code, Codex, or many providers in legacy mode) to autonomously run security tools and reason through multi-stage pentest and CTF pipelines. It is a Python CLI tool published at USENIX Security 2024, with session persistence and live step tracking.

Use cases

• automate penetration testing with an LLM agent
• solve CTF challenges automatically
• run reconnaissance and exploitation pipelines with AI
• generate penetration testing reports from findings
• get AI guidance during interactive pentesting sessions
• test web, crypto, reversing, forensics, and pwn challenges

When to choose

• you want an autonomous LLM-driven agent to run pentest or CTF workflows end to end
• you need multi-provider LLM support including local Ollama in interactive mode
• you want research-backed tooling with session persistence and staged pipelines

When to avoid

• you need a passive vulnerability scanner rather than an agentic tool driver
• you cannot expose LLM access to sensitive target environments
• you require a GUI-based pentesting platform
• your use case is defensive security monitoring rather than offensive testing

Facets

cli-tool · maturity active

penetration-testing agent-framework llm-inference security cli security penetration-testing artificial-intelligence large-language-models python cli cross-platform ctf autonomous-agent llm-agent offensive-security vulnerability-assessment ai-agents linux macos

Member repositories

For agents

markdown · JSON · MCP: product_card(name="GreyDGL/PentestGPT")