repowisevxcontrol/pentagi

vxcontrol / pentagi

Fully autonomous AI Agents system capable of performing complex penetration testing tasks

Go★ 25,689
Use in your agentAsk this codebase

github.com/vxcontrol/pentagiIndexed at 843dfebUp to date with upstream

What is pentagi?

pentagi is a self-hosted multi-agent system for autonomous penetration testing. You describe a target and goal in plain language, and specialized AI agents plan the work, run security tools in an isolated Docker sandbox, retain findings, and produce a report. The project is primarily written in Go, with a TypeScript frontend and npm tooling.

Written by a model from the README and the source

1,475 files and 14,297 symbols in 6 modules, led by Go (645 files) and TypeScript (524).

Start reading

Code health

7.5out of 10Good

This codebase scores 7.5 out of 10 for code health, which we rate good. It also scores maintainability 7.3 and static performance 9.8 out of 10. The three are scored separately and never blended into one number. Risk is concentrated, as it usually is: 113 of 1,475 files are git hotspots, and they average 6.0 — which is where the fixes pay off most.

Full health report

On the leaderboards:#2 of 22 Go repos

Use vxcontrol/pentagi in your agent

Point Claude Code, Cursor, Codex or VS Code at this repository. Your agent gets the index this page is built from: cited answers, callers, history and health for any file.

  1. 1.In Claude, open Customize → Connectors, click +, then Add custom connector. On a Team or Enterprise plan an owner adds it first under Organization settings → Connectors.
  2. 2.Paste the server URL below as the Remote MCP server URL, then click Add.
  3. 3.Click Connect. A Repowise sign-in window opens. Approve access.
  4. 4.Repowise's tools are now available in your Claude chats.

Connect with one click. Sign in with Repowise (OAuth), no API key to copy. Works in Claude on the web, desktop, and mobile.

Docs
bash
https://api.repowise.dev/mcp/vxcontrol/pentagi
Editors need an API key: sign in to create one.Sign in to connect

This repo is public, so anyone with a Repowise account and an API key can connect.

Try asking

  • get_overview()
  • get_answer("how is pentagi put together?")
  • get_why("why is pentagi structured this way?")

Explore pentagi

Key features of pentagi

  • Pentagi runs penetration testing operations inside an isolated Docker environment.
  • Pentagi uses specialized AI agents to plan and execute penetration testing steps.
  • Pentagi includes professional security tools such as nmap, Metasploit, and sqlmap.
  • Pentagi stores research results and successful approaches for future use.
  • Pentagi provides REST and GraphQL APIs with Bearer token authentication.
  • Pentagi generates vulnerability reports with exploitation guides.

How vxcontrol/pentagi works

Input enters through the browser-facing frontend in frontend, where React pages, features, and shared components provide the user interface. The backend/cmd subsystem provides command entry points, including an interactive installer and test utilities. The backend/pkg subsystem coordinates configuration, providers, controllers, observability, and the server that processes requests. backend/pkg routes request flow through providers and controllers while recording spans and events through its observability layer. The frontend/src directory organizes UI pages, feature state, and shared interaction components. backend/cmd/ctester drives checks for model and agent behavior, tool execution, and indexed search, then formats the results.

The codebase has 1,475 files and 14,297 symbols in 6 modules, led by Go, TypeScript and Shell. Code health is 7.5 out of 10, rated good.

Getting started with pentagi

  1. Create the installation directory and enter it.
    mkdir -p pentagi && cd pentagi
  2. Extract the installer archive.
    unzip installer.zip

Commands copied from the README

vxcontrol/pentagi FAQ

What is pentagi?

pentagi is a self-hosted multi-agent system for autonomous penetration testing. It accepts a target and goal in plain language and produces a penetration testing report.

How does pentagi work?

pentagi coordinates specialized AI agents that plan tasks, run security tools in an isolated Docker sandbox, retain research results, and generate reports.

How do I install pentagi?

pentagi provides an interactive installer for Linux, macOS, and Windows. On Linux amd64, download and extract the installer, then run ./installer.

What language is pentagi written in?

pentagi is primarily written in Go. Its browser-facing frontend uses TypeScript.

How is pentagi organized?

pentagi is organized into backend and frontend modules. backend/pkg coordinates server functionality, backend/cmd provides command entry points, and frontend/src contains React pages, features, and shared components.

Who is pentagi for?

pentagi is for security engineers, penetration testers, researchers, and red teams conducting authorized testing on their own infrastructure.

What license does pentagi use?

pentagi uses the MIT license.

The summary, features and answers on this page are written by a model from the README and the source, and refreshed with each index.

About this page

Get a page like this for your own codebase

Repowise built this map of vxcontrol/pentagi from its source and git history. It parses every symbol, draws the dependency graph, scores each file's health from complexity, duplication, coverage and churn, finds hotspots and owners in the history, and writes documentation for every module. Your coding agent reads the same index over MCP, so its answers cite real files.

Index your repo freeSee how Repowise worksFree for 2 public repos, with a page like this one.

Prefer local? pip install repowise && repowise init indexes your own checkout, no account needed.