PentAGI
Self-hosted multi-agent system that runs penetration tests with common security tools inside a Docker sandbox
Agent by VXControl
IndexedMIT★ 32,256
Get started
Setup steps are in the repository. Website · Repository
About
PentAGI is an open-source multi-agent system for autonomous penetration testing that you host yourself. You describe a target and a goal in plain language, and a team of specialised agents plans the work and runs more than 20 tools such as nmap, Metasploit and sqlmap inside an isolated Docker sandbox. Past results are kept in PostgreSQL with pgvector, an optional Neo4j knowledge graph tracks hosts and services, and it produces a report at the end.
Use cases: security, security-scanning
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Fact sheet
- Jobs
- securityREADME
- Autonomy
- Autonomous: runs tasks end to end and reports backREADME
- Hosting
- You run itREADME
- Models
- openai, anthropic, google, aws-bedrock, azure-openai, deepseek, mistral, xai, ollama, vllm, glm, kimi, qwen, minimaxREADME
- Open source
- YesREADME
Facts extracted by Claude Sonnet 5.5 from the linked sources on Oct 24, 2026; reviewed Oct 24, 2026. Wrong fact? Tell us.
Signals
- Stars
- 32,256
- Forks
- 5,002
- Open issues
- 23
- Last commit
- Oct 22, 2026 (6 days ago)
- Last release
- Oct 5, 2026 (23 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/vxcontrol/pentagi
- Website
- pentagi.com
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- READMEgithub-graphql
Cite this page
PentAGI. Agent Mart. https://agentmart.dev/agents/pentagi (last updated 2026-10-24)