⬢github Go · 29K ★ +375 since we first saw it · pushed 4 d ago · MIT
vxcontrol/pentagi
Fully autonomous AI Agents system capable of performing complex penetration testing tasks
PentAGI is an open-source, self-hosted system of autonomous AI agents that performs complex penetration testing tasks. Built in Go with a React frontend, it supports many LLM providers (OpenAI, Anthropic, Ollama, Gemini, and others), runs agents in isolated Docker environments, and includes observability, knowledge graph, and OAuth integrations for security workflows.
Why now: It's rapidly trending — nearly 29k stars and multiple Trendshift badges (daily/weekly/monthly) indicate it's riding current interest in autonomous AI agents for offensive security.
Who it is for: Security researchers, ethical hackers, and red-team professionals looking to automate penetration testing with LLM-driven agents.
ai-agentsai-security-toolanthropicautonomous-agentsgolanggptgraphqlmulti-agent-systemoffensive-securityopen-source
Stars over our 22 snapshots: 28.6K to 29K, since 5 h ago.
Where people talked about it
- ⬢github vxcontrol/pentagi 11 min ago
API: https://socialmediatrends-api.osmike.com/v1/repos/vxcontrol/pentagi