PentAGI
ActiveDescription
Fully autonomous AI Agents system capable of performing complex penetration testing tasks using multi-agent architecture with support for multiple LLM providers.
Key Features
- Fully autonomous AI agent for penetration testing with intelligent task planning
- Sandboxed Docker environment ensuring complete isolation of all operations
- 20+ built-in professional security tools including nmap, metasploit, and sqlmap
- Knowledge graph integration via Graphiti for semantic relationship tracking
- Multi-provider LLM support: OpenAI, Anthropic, Gemini, Bedrock, Ollama, and more
- Comprehensive monitoring with Grafana/Prometheus and detailed vulnerability reporting
Use Cases
💡 Automated security assessment of web applications and network infrastructure
💡 Vulnerability discovery and exploitation with detailed reporting
💡 Security research and penetration testing for ethical hackers
💡 Team-based security operations with specialized AI agent delegation
💡 Continuous security monitoring with real-time Grafana dashboards
Strengths & Limitations
✅ Strengths
- • Actively maintained, recent updates
- • High community interest (22.3k stars)
- • Permissive open-source license (MIT)
- • Responsive to issues, low backlog
Tags
Categories
Quick Start
git clone https://github.com/vxcontrol/pentagi.git
cd pentagi
docker compose up -d
# Access the web UI at http://localhost:8080