{"name":"pentagi","repo":"vxcontrol/pentagi","url":"https://midorreal.com/project/vxcontrol-pentagi","repository":"https://github.com/vxcontrol/pentagi","description":"Fully autonomous AI Agents system capable of performing complex penetration testing tasks","facts":{"license":{"value":"MIT","source":"https://github.com/vxcontrol/pentagi","checked":"22 Nov 2026"},"language":{"value":"Go","source":"https://github.com/vxcontrol/pentagi","checked":"22 Nov 2026"},"homepage":{"value":"https://pentagi.com","source":"https://pentagi.com","checked":"22 Nov 2026"},"last_release":{"value":"v2.2.0, 5 Oct 2026","source":"https://github.com/vxcontrol/pentagi/releases","checked":"22 Nov 2026"},"releases":{"value":"10","source":"https://github.com/vxcontrol/pentagi/releases","checked":"19 Nov 2026"},"contributors":{"value":"17","source":"https://github.com/vxcontrol/pentagi/graphs/contributors","checked":"19 Nov 2026"},"archived":{"value":"no","source":"https://github.com/vxcontrol/pentagi","checked":"22 Nov 2026"}},"stars":34767.0,"writeup":{"what_it_is":"PentAGI is an open-source, self-hosted multi-agent system for autonomous penetration testing. Users describe a target and goal in plain language; specialized AI agents plan and execute testing using 20+ professional tools like nmap, Metasploit, and sqlmap in an isolated Docker sandbox, then deliver a report.","audience":"Security engineers, penetration testers, researchers, and red teams","claims":[{"kind":"specific","claim":"Runs 20+ professional security tools","excerpt":"runs 20+ professional tools such as nmap, Metasploit and sqlmap inside an isolated Docker sandbox","status":"not_checked"},{"kind":"specific","claim":"Supports 10+ LLM providers and custom endpoints","excerpt":"10+ cloud LLM providers, your own OpenAI-compatible gateway, or local models through Ollama or vLLM","status":"not_checked"},{"kind":"specific","claim":"Stores results in PostgreSQL with pgvector","excerpt":"Results and successful approaches are kept in PostgreSQL with pgvector for later flows","status":"not_checked"},{"kind":"specific","claim":"Includes optional Neo4j knowledge graph for tracking hosts, services and findings","excerpt":"an optional Neo4j knowledge graph tracks hosts, services and findings","status":"not_checked"},{"kind":"specific","claim":"Provides REST and GraphQL APIs","excerpt":"REST and GraphQL APIs automate it","status":"not_checked"}],"alternatives":[{"name":"strix","url":"https://midorreal.com/project/usestrix-strix"},{"name":"Anthropic-Cybersecurity-Skills","url":"https://midorreal.com/project/mukul975-anthropic-cybersecurity-skills"}],"written_by":"AI, from the project's README","date":"2026-10-12"},"why_now":null,"owner_supplied":null,"score":{"verdict":"too_early","hype":85,"reality":10,"gap":75,"momentum":0.7,"confidence":60,"version":"score-2.0","rule":"verdict-2.0","calculated_at":"2026-11-22T07:00:00+00:00","verdict_source":"rule"},"early_read":{"estimate":true,"lean":"too_close","gap_low":null,"gap_high":null,"rule":"early-2.0"},"changes":[{"date":"2026-10-05T06:59:50+00:00","text":"Latest release v2.2.0","source":"https://github.com/vxcontrol/pentagi/releases"},{"date":"2025-01-07T01:26:34+00:00","text":"First release","source":"https://github.com/vxcontrol/pentagi/releases"},{"date":"2025-01-06T22:22:48+00:00","text":"Repository created","source":"https://github.com/vxcontrol/pentagi"}],"cite":"pentagi is a GitHub project at https://github.com/vxcontrol/pentagi written mainly in Go, described there as \"Fully autonomous AI Agents system capable of performing complex penetration testing tasks\".","attribution":"Data from Mid or Real, https://midorreal.com/project/vxcontrol-pentagi, checked 22 November 2026. Attribution with a link is required.","still_real":null}