PentAGI is a self-hosted AI agent system that automates complex penetration testing tasks within an isolated Docker sandbox. It is designed for operations teams and developers who need autonomous security testing paired with detailed vulnerability reporting.
Project overview
The system combines an autonomous AI agent for multi-step penetration testing with an integrated suite of over 20 professional security tools in a sandboxed environment.
Project type
AI Agent · Workflow
Use cases
Automation
Deployment
Refer to project documentation
License
MIT
Best for
Operations teams and developers seeking an autonomous, self-hosted AI agent system for executing complex penetration testing tasks in an isolated Docker environment.
Key capabilities
All operations are performed in a sandboxed Docker environment.
AI-powered agent that automatically determines and executes penetration testing steps.
Built-in suite of 20+ professional security tools including nmap, metasploit, sqlmap, and more.
Long-term storage of research results and successful approaches for future use.
Built-in browser via scraper for gathering latest information from web sources.
Generation of thorough vulnerability reports with exploitation guides.
Delegation system with specialized AI agents for research, development, and infrastructure tasks.
Full-featured REST and GraphQL APIs with Bearer token authentication for automation and integration.
Limitations and risks
PentAGI is an autonomous penetration testing platform, not a CALDERA-style Breach and Attack Simulation (BAS) or adversary emulation product.
The Neo4j integration via Graphiti is currently a beta feature and has notable provider limitations.
Even when a flow runs against a non-OpenAI provider, Graphiti still incurs cost on the configured OpenAI-compatible endpoint.
Getting started
Download the installer, run the interactive installer with a terminal-based UI, start containers, and open the Web UI. Coding is not required for setup.
Evidence and sources
README: Fully Autonomous. AI-powered agent that automatically determines and executes penetration testing steps with optional execution monitoring and intelligent task planning for enhanc…
README: PentAGI provides an interactive installer with a terminal-based UI for streamlined configuration and deployment.
README: Fill in the required API keys in `.env` file.
README: PentAGI today is an autonomous and assistant-guided penetration testing platform, not a CALDERA-style Breach and Attack Simulation (BAS) or adversary emulation product with predef…
README: - Docker and Docker Compose (or Podman - see [Podman configuration](#running-pentagi-with-podman)) - Minimum 2 vCPU - Minimum 4GB RAM - 20GB free disk space - Internet access for…