vxcontrol/pentagi

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

About the project

vxcontrol/pentagi is an AI system that carries out penetration-testing tasks using multiple agents and security tools inside isolated Docker environments. It is intended for information-security professionals, researchers, and ethical hackers who automate security testing. The catalogue includes an instruction for working with PentAGI.

Latest release v2.1.0 — 2.1.0 · 29 May 2026

These files are vxcontrol/pentagi's own configuration. They tell Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.

22,355Stars on the repository
1Files it configures its agents with
2,308Tokens loaded in every session
1Agent configured

Instructions