vxcontrol/pentagi

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

What it solves

PentAGI provides an automated system for conducting penetration tests, reducing the manual effort required for security researchers and ethical hackers to identify vulnerabilities in target systems.

How it works

It uses a multi-agent AI system where specialized agents (Researcher, Developer, and Executor) collaborate to analyze targets, plan attacks, and execute security tools. The system operates within a sandboxed Docker environment for security and isolation, utilizing a vector store (PostgreSQL with pgvector) and an optional knowledge graph (Neo4j) for long-term memory and context tracking. It integrates with various LLM providers and external search APIs to gather intelligence and determine the best course of action.

Who it’s for

Information security professionals, security researchers, and ethical hacking enthusiasts.

Highlights

  • Autonomous Execution: AI agents automatically determine and execute penetration testing steps with intelligent task planning.
  • Professional Toolset: Built-in access to over 20 professional security tools, including nmap, metasploit, and sqlmap.
  • Secure Sandboxing: All operations are performed in isolated Docker containers to protect the host system.
  • Extensive Integrations: Supports a wide array of LLM providers (OpenAI, Anthropic, Gemini, etc.) and search systems (Tavily, Perplexity, Google, etc.).
  • Comprehensive Reporting: Generates detailed vulnerability reports complete with exploitation guides.

Related

  • Project
    GH05TCREW/pentestagent

    An AI-powered penetration testing framework that automates security assessments using autonomous agents, multi-agent orchestration, and MCP-integrated security tools.

  • Project
    SHAdd0WTAka/Zen-Ai-Pentest

    An autonomous, AI-driven penetration testing framework that orchestrates over 72 security tools to automate reconnaissance, exploitation, and reporting.

  • Project
    pensarai/apex

    An AI-powered penetration testing tool that uses autonomous agents to perform blackbox and whitebox security audits directly from the terminal.

  • Project
    Autumn-27/ARTEX

    An AI-driven autonomous penetration testing system that uses a multi-agent architecture and dual-graph tracking to automate vulnerability discovery and complex attack chains.

  • Project
    bugbasesecurity/pentest-copilot

    An AI-driven penetration testing agent that autonomously runs security tools on a Kali attack box, analyzes results, and iterates to find vulnerabilities.