# GreyDGL/PentestGPT

Automated Penetration Testing Agentic Framework Powered by Large Language Models

Repository: https://github.com/GreyDGL/PentestGPT
Canonical: https://ross.abutalabs.com/products/pentestgpt
Language: Python
License: MIT
License Family: permissive
Topics: penetration-testing, python, large-language-models, llm
Last push: 2026-07-14T12:58:31+00:00

## Health v2 (maintenance only)
Score: 70/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 92, release rhythm 30, longevity 91
- inputs: {"age_days": 1283, "days_push": 50, "days_rel": 252, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 15091, forks 2632 (observed 2026-08-28T04:11:09.135228+00:00)

## What it is
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
- artifact type: cli-tool
- maturity: active
- function: penetration-testing, agent-framework, llm-inference, security, cli
- domain: security, penetration-testing, artificial-intelligence, large-language-models
- platform: python, cli, cross-platform
- tags: ctf, autonomous-agent, llm-agent, offensive-security, vulnerability-assessment, ai-agents, linux, macos

## Member repositories
- GreyDGL/PentestGPT (main) score 70

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:09.135228+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:06:44.519206+00:00, confidence not recorded.
  - readme: https://github.com/GreyDGL/PentestGPT (fetched 2026-08-28T04:11:09.135228+00:00, sha 57b9be12af27)
  - registry_pypi: https://pypi.org/pypi/pentestgpt/json (fetched 2026-08-29T08:04:39.835697+00:00, sha 1796f78a3d32)
- Data as of 2026-08-30T08:39:29.467469+00:00.