Artificial intelligence for autonomous penetration testing
Developed with the Go language, Pentagi offers a system of fully autonomous artificial intelligence agents (AI agents) that can perform complex penetration testing. The system aims to standardize autonomous workflows to detect and exploit vulnerabilities.
Updates
- November 4, 2026: Stars 31,649 → 33,238, latest release v2.2.0 (October 5, 2026).
- October 21, 2026: Stars 30,107 → 31,649, latest release v2.2.0 (October 5, 2026).
- October 15, 2026: Stars 28,092 → 30,107, latest release v2.2.0 (October 5, 2026).
- October 13, 2026: Stars 26,612 → 28,092, latest release v2.2.0 (October 5, 2026).
What you get
- Fully autonomous security tests in Sandboxed Docker environment
- Support for more than 20 professional tools such as Nmap and SQLmap
- Detailed system monitoring with Grafana and Prometheus
Running it
curl -O https://raw.githubusercontent.com/vxcontrol/pentagi/master/docker-compose.yml
docker compose up -dIf you don't write code
I want to initiate an autonomous penetration test on the target system using the PentAGI system. How can I configure the necessary workflow for this artificial intelligence agent running in the Docker environment to detect security vulnerabilities, scan using tools such as nmap and sqlmap, and present the findings in a detailed report?
Repository: https://github.com/vxcontrol/pentagi. Follow the official instructions in the README of this repository for setup and execution.
Before starting, check which OS we are on and if the necessary tools (e.g., Python, Node.js, Git, Docker) are installed. Install any missing ones step-by-step according to this system.
Create a new, empty folder to work in. Do not touch any files outside this folder and do not delete anything. Tell me what you are going to do in one sentence before running each command.
Tell me what I should see on the screen at the end of each step. If an error occurs, I will paste the error message to you exactly as it is, and we will fix it together.
Related dictionary terms
Links
TreScout did not build this tool · we found it in GitHub trends and wrote it up. This page describes the repository as of 2026-07-10: The star count and our text belong to that day, the repository may have changed since. Check the repository link for the current state. The introductory text was prepared with AI from the repository's own documentation, and this page was machine-translated from the Turkish original · the Turkish version prevails.