PentAGI is a fully autonomous AI agent system for penetration testing. Multiple specialized AI agents (researchers, developers, executors) collaborate to conduct automated security assessments in isolated Docker environments. Integrates with 10+ LLM providers, features persistent knowledge storage via vector embeddings, real-time monitoring through Grafana/Prometheus, and Langfuse observability. Multi-layered supervision prevents infinite loops and optimizes agent performance.
git clone https://github.com/vxcontrol/pentagi.git
# Run PentAGI
git clone https://github.com/vxcontrol/pentagi
cd pentagi
docker compose up -d
# Access dashboard at http://localhost:3000
# Configure LLM provider and target
# Launch autonomous pentest