vxcontrol/pentagi
Fully autonomous AI Agents system capable of performing complex penetration testing tasks
From the publisher
README & documentation
Source previewRead the project’s overview, installation instructions and usage examples. The original README is the source of truth.
[](https://discord.gg/2xrMh7qX6m)⠀[](https://t.me/+Ka9i6CNwe71hMWQy) PentAGI is an open-source, self-hosted multi-agent system for autonomous penetration testing. You describe a target and a goal in plain language; a team of specialized AI agents plans the work, runs 20+ professional tools such as nmap, Metasploit and sqlmap inside an isolated Docker sandbox, remembers what it learned and hands you a report. PentAGI is developed by VXControl, a security engineering company based in Dubai. You can watch the video PentAGI overview: [](https://youtu.be/R70x5Ddzs1o) Container Architecture (click to expand) Entity Relationship (click to expand) Agent Interaction (click to expand) Memory System (click to expand) Chain Summarization (click to expand) The chain summarization system manages conversation context growth by selectively summarizing older messages. This is critical for preventing token limits from being exceeded while maintaining conversation coherence. The algorithm operates on a structured representation of conversation chains (ChainAST) that preserves message types including tool calls and their responses. All summarization…
Read the full README ↗ · Preview checked 2026-10-27T03:18:18.535Z
Inside the original README — Document outline
- PentAGI
- Table of Contents
- Overview
- Features
- Current Capability Boundaries
- Architecture
- System Context
- Global Summarizer Configuration Options
- Assistant Summarizer Configuration Options
- Summarizer Environment Configuration
- Execution Monitoring (Beta)
- Intelligent Task Planning (Beta)
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the README
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: MIT. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
What this repository does
Fully autonomous AI Agents system capable of performing complex penetration testing tasks
Repository facts
- Owner
- vxcontrol
- Primary language
- Go
- Stars
- 32,902
- Forks
- 5,141
- Open issues + pull requests
- 63
- License
- MIT
- Archived
- No
- Default branch
- main
- Created
- 2025-01-06T22:22:48.000Z
- Last push
- 2026-10-22T23:26:13.000Z
Topics and intended use
Owner-supplied topics: ai-agents, ai-security-tool, anthropic, autonomous-agents, golang, gpt, graphql, multi-agent-system, offensive-security, open-source, openai, penetration-testing, penetration-testing-tools, react, security-automation, security-testing, security-tools, self-hosted
Review the README for scope, installation, examples and limitations. We do not run repository code or certify it.
Evaluate before installing
Review licensing and dependencies, inspect recent commits and unresolved issues, and test in an isolated environment before production use. Stars and forks alone cannot answer these questions.
Source and freshness
Source: GitHub. Metadata observed 2026-11-01T12:20:37.856Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.