pentagi

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

⭐ 17,333 stars on GitHub · 🍴 2,377 forks · 📜 License: mit · 💻 Language: Go

What is pentagi?

Automating security audits requires more than just chaining scripts together—it demands intelligent decision-making and safe execution. By combining a multi-agent LLM architecture with sandboxed Docker environments, you get an autonomous penetration testing system that actively reasons

Topics: the project is tagged with popular topics:

• 🏷️ ai-agents
• 🏷️ ai-security-tool
• 🏷️ anthropic
• 🏷️ autonomous-agents
• 🏷️ golang
• 🏷️ gpt
• 🏷️ graphql
• 🏷️ multi-agent-system
• 🏷️ offensive-security
• 🏷️ open-source

📸 Screenshots

Quick install

The project supports Docker Compose:

git clone https://github.com/vxcontrol/pentagi.git
cd pentagi
docker compose up -d

Check the README in the repo for required env variables.

Minimum system requirements

⚡ Deploy fast on VSIS

Use the VSIS VPS Lite 2GB RAM / 2 vCPU / 25GB SSD (~104k/tháng) plan from VSIS.NET — high-speed VN-based VPS, 24/7 support, ideal for running pentagi smoothly.

🎯 Benefits:

• One-command docker compose up -d deploy in 2 minutes
• Dedicated IPv4, root access, unmetered domestic bandwidth
• Daily snapshot backup
• Free install assistance from the VSIS team

👉 See matching VPS plans at vsis.net

Resources

• 🔗 GitHub: vxcontrol/pentagi
• 🌐 Homepage: https://pentagi.com
• 📚 Official docs: see README in the repo
• 💬 Community: GitHub Issues + Discussions

Article compiled from GitHub data on 30/05/2026. Star/fork counts may have changed — see live numbers via the GitHub link.