pentagi is a free, open source threat detection & response project written in Go and released under MIT. It has 24,708 GitHub stars, 3,177 forks and 71 open issues, and was last pushed 9 days ago. On this registry it ranks #4 of 12 tracked projects in Threat Detection & Response, with 5 head-to-head comparisons available.

What is pentagi?

PentAGI is an MIT-licensed, self-hosted multi-agent system written in Go that runs fully autonomous AI agents to perform complex penetration testing tasks inside an isolated Docker sandbox, built for information security professionals, researchers, and enthusiasts.

What it is

PentAGI is an autonomous penetration testing system that lives in the self-hosted Docker ecosystem. The backend is written in Go, the interface is React, and the project exposes a GraphQL API alongside a web UI and an agent interface. Agents operate inside a sandboxed Docker environment with complete isolation, and the project supports a range of model backends including Ollama, OpenAI, Anthropic, Google AI (Gemini), AWS Bedrock, DeepSeek, GLM, Kimi, Qwen, and MiniMax. Deployment is self-hosted, with optional integration paths for Langfuse, Grafana/Prometheus, Neo4j-backed knowledge graphs, and GitHub or Google OAuth.

The concrete problem it solves is the manual, operator-driven orchestration of separate penetration testing tools. Instead of a human chaining commands across nmap, metasploit, sqlmap and the rest, PentAGI's agents determine and execute the testing steps themselves, with optional execution monitoring and intelligent task planning. The project ships a built-in suite of 20+ professional security tools, a smart memory system that stores research results and successful approaches for future runs, and a delegation model in which specialized agents handle research, development, and infrastructure work. That combination replaces the tool-by-tool workflow with a single autonomous loop that plans, executes, remembers, and reports.

Key capabilities

  • Sandboxed execution: all operations run inside an isolated Docker environment, with a documented approach for giving agents Docker access without exposing the host.
  • Fully autonomous agent loop that determines and executes penetration testing steps, with optional execution monitoring and intelligent task planning for reliability.
  • Built-in suite of more than 20 professional security tools, including nmap, metasploit, and sqlmap.
  • Smart memory system for long-term storage of research results and successful approaches, plus optional Graphiti-powered knowledge graph on Neo4j for semantic relationship tracking.
  • Web intelligence through a built-in browser using the vxcontrol/scraper image, backed by external search integrations including Tavily, Firecrawl, Traversaal, Perplexity, DuckDuckGo, Google Custom Search, Sploitus Search, and Searxng.
  • Delegation system with specialized agents for research, development, and infrastructure tasks, designed to work well with smaller models.
  • Operational plumbing: GraphQL API access, Grafana/Prometheus monitoring, Langfuse integration, GitHub and Google OAuth, and multi-instance operation through tenant_id.

Who uses it and how

  • Information security professionals and researchers running authorized penetration tests who want the planning and execution loop automated rather than driven by hand.
  • Teams with local or private model infrastructure, using the Ollama provider configuration to keep testing traffic off third-party APIs.
  • Larger security operations that need observability, wiring Grafana/Prometheus for real-time metrics and Langfuse for model tracing.
  • Multi-tenant setups running several isolated instances on one host, separated by tenant_id.
  • Assessors who need fresh external context, relying on the bundled browser and the search API integrations during reconnaissance.

Getting started

The README provides a Quick Start path for self-hosted deployment, with Docker image configuration documented alongside it; auxiliary images such as vxcontrol/scraper are pulled as needed. The project homepage at https://pentagi.com and the linked video overview cover the same first-run flow.

How it compares

The provided facts name no paid products this project replaces, and no directly comparable open-source tools. Within this registry it stands alone in its category.

When to use it — and when not to

A self-hoster must operate a Docker host capable of isolated agent workloads, supply credentials for at least one LLM provider, and optionally run Neo4j for the knowledge graph plus Grafana/Prometheus and Langfuse for monitoring. Anyone who cannot isolate agent network access, or who lacks model API budget and search API keys, should not pick it. The project also carries 71 open issues and the README excerpt ends abruptly, so expect to lean on the Discord and Telegram community channels for support.

project readme (upstream, from github) — read inline

PentAGI

Penetration testing Artificial General Intelligence


Join the Community! Connect with security researchers, AI enthusiasts, and fellow ethical hackers. Get support, share insights, and stay updated with the latest PentAGI developments.

DiscordTelegram

vxcontrol%2Fpentagi | Trendshift

Table of Contents

Overview

PentAGI is an innovative tool for automated security testing that leverages cutting-edge artificial intelligence technologies. The project is designed for information security professionals, researchers, and enthusiasts who need a powerful and flexible solution for conducting penetration tests.

You can watch the video PentAGI overview: PentAGI Overview Video

Features

  • Secure & Isolated. All operations are performed in a sandboxed Docker environment with complete isolation.
  • Fully Autonomous. AI-powered agent that automatically determines and executes penetration testing steps with optional execution monitoring and intelligent task planning for enhanced reliability.
  • Professional Pentesting Tools. Built-in suite of 20+ professional security tools including nmap, metasploit, sqlmap, and more.
  • Smart Memory System. Long-term storage of research results and successful approaches for future use.
  • Optional Knowledge Graph Integration. Graphiti-powered knowledge graph using Neo4j for semantic relationship tracking and advanced context understanding.
  • Web Intelligence. Built-in browser via scraper for gathering latest information from web sources.
  • External Search Systems. Integration with advanced search APIs including Tavily, Firecrawl, Traversaal, Perplexity, DuckDuckGo, Google Custom Search, Sploitus Search and Searxng for comprehensive information gathering.
  • Team of Specialists. Delegation system with specialized AI agents for research, development, and infrastructure tasks, enhanced with optional execution monitoring and intelligent task planning for optimal performance with smaller models.
  • Comprehensive Monitoring. Detailed logging and integration with Grafana/Prometheus for real-time system observation.
  • Detailed Reporting. Generation of thorough vulnerability reports with exploitation guides.
  • Smart Container Management. Automatic Docker image selection based on specific task requirements.
  • Modern Interface. Clean and intuitive web UI for system management and monitoring.
  • Comprehensive APIs. Full-featured REST and GraphQL APIs with Bearer token authentication for automation and integration.
  • Persistent Storage. All commands and outputs are stored in PostgreSQL with pgvector extension.
  • Scalable Architecture. Microservices-based design supporting horizontal scaling.
  • Self-Hosted Solution. Complete control over your deployment and data.
  • Flexible Authentication. Support for 10+ LLM providers (OpenAI, Anthropic, Google AI/Gemini, AWS Bedrock, Ollama, DeepSeek, GLM, Kimi, Qwen, MiniMax, Custom) plus aggregators (OpenRouter, DeepInfra, Atlas Cloud, OpenCode Go plan). For production local deployments, see our vLLM + Qwen3.5-27B-FP8 guide.
  • API Token Authentication. Secure Bearer token system for programmatic access to REST and GraphQL APIs.
  • Quick Deployment. Easy setup through Docker Compose with comprehensive environment configuration.

Current Capability Boundaries

  • PentAGI today is an autonomous and assistant-guided penetration testing platform, not a CALDERA-style Breach and Attack Simulation (BAS) or adversary emulation product with predefined campaigns or attack plans.
  • BAS-like agent-authored attack scripts should be treated as conceptual or future work, not as a feature that is implemented today.
  • The current flow report UI supports web view, copy to clipboard, Markdown download, and PDF download. JSON flow-report export is not documented as a supported output format today.
  • Provider flexibility is available today through built-in providers and custom/OpenAI-compatible endpoints. See Custom LLM Provider Configuration and the vLLM + Qwen3.5-27B-FP8 guide.

Architecture

System Context

flowchart TB
    classDef person fill:#08427B,stroke:#073B6F,color:#fff
    classDef system fill:#1168BD,stroke:#0B4884,color:#fff
    classDef external fill:#666666,stroke:#0B4884,color:#fff

    pentester["👤 Security Engineer
    (User of the system)"]

    pentagi["✨ PentAGI
    (Autonomous penetration testing system)"]

    target["🎯 target-system
    (System under test)"]
    llm["🧠 llm-provider
    (OpenAI/Anthropic/Ollama/Bedrock/Gemini/Custom)"]
    search["🔍 search-systems
    (Google/DuckDuckGo/Tavily/Firecrawl/Traversaal/Perplexity/Sploitus/Searxng)"]
    langfuse["📊 langfuse-ui
    (LLM Observability Dashboard)"]
    grafana["📈 grafana
    (System Monitoring Dashboard)"]

    pentester --> |Uses HTTPS| pentagi
    pentester --> |Monitors AI HTTPS| langfuse
    pentester --> |Monitors System HTTPS| grafana
    pentagi --> |Tests Various protocols| target
    pentagi --> |Queries HTTPS| llm
    pentagi --> |Searches HTTPS| search
    pentagi --> |Reports HTTPS| langfuse
    pentagi --> |Reports HTTPS| grafana

    class pentester person
    class pentagi system
    class target,llm,search,langfuse,grafana external

    linkStyle default stroke:#ffffff,color:#ffffff
Container Architecture (click to expand)
graph TB
    subgraph Core Services
        UI[Frontend UI<br/>React + TypeScript]
        API[Backend API<br/>Go + GraphQL]
        DB[(Vector Store<br/>PostgreSQL + pgvector)]
        MQ[Task Queue<br/>Async Processing]
        Agent[AI Agents<br/>Multi-Agent System]
    end

    subgraph Knowledge Graph
        Graphiti[Graphiti<br/>Knowledge Graph API]
        Neo4j[(Neo4j<br/>Graph Database)]
    end

    subgraph Monitoring
        G

readme truncated — read the full docs on github

Frequently asked questions

Is pentagi free to use?

pentagi is open source under the MIT licence. There is no licence fee and no seat count — you can self-host it or, where the project offers one, pay a vendor for a managed version instead.

What does pentagi do?

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

What is pentagi written in?

pentagi is primarily written in Go. Its source is publicly available at https://github.com/vxcontrol/pentagi, and it has 24,708 GitHub stars.