pentagi

Community

Autonomous multi-agent pentesting in Docker.

Authorstevengonsalvez
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Penetration testing often requires costly, manual, and multi-tool coordination. This Skill automates autonomous pentesting workflows using AI-driven agents in a Docker-based environment, enabling contained, repeatable security assessments.

Core Features & Use Cases

  • Multi-agent orchestration coordinates discovery, planning, execution, and memory updates across tools.
  • Sandboxed Docker execution with a knowledge graph memory to improve reuse and learning from past engagements.
  • 20+ built-in security tools enable comprehensive vulnerability scanning and exploitation planning.
  • Use Cases: security teams perform autonomous pentests against test targets while maintaining strict containment and audit trails.

Quick Start

Start the pentagi stack by running docker compose up -d in the ~/d/git/pentagi directory.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: pentagi
Download link: https://github.com/stevengonsalvez/nanoclaw-standalone/archive/main.zip#pentagi

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.