PentAGI
PentAGI is a self-hosted agent app that runs automated penetration tests against a target you describe in plain language, for security professionals.
What it is good for
- Running automated security tests on systems you are authorized to test
- Scanning hosts and services for vulnerabilities with common security tools
- Writing vulnerability reports with exploitation guides
- Keeping test findings and past approaches for later testing
At a glance
- Who it is for
- Setup
- Guided command-line setup
Level 4 of 5. You copy and paste commands into a terminal by following the instructions. Comfortable territory for vibe coders.
- Cost
- Free and open source
- Type
- Agent app
- Tasks
- Works with
- Docker Compose, OpenAI, Anthropic, Google AI (Gemini), Ollama, Metasploit
Momentum
- Rank this week
- Not ranked (last #13, week 42, 2026)
- Best rank
- #13 week 42, 2026
- GitHub stars
- 32,991
GitHub numbers as of Nov 2, 2026. Updated weekly.
Ranking history
Official links
Setup steps are on the official pages. We do not repeat them here, since they change.
Questions
- Is PentAGI free?
- Yes. It is free and open source (MIT license).
- Do I need to know how to code to use PentAGI?
- You do not need to write code, but setup means copying and pasting commands into a terminal by following its instructions.
- What does PentAGI work with?
- According to its own documentation, it works with Docker Compose, OpenAI, Anthropic, Google AI (Gemini), Ollama, and Metasploit.
- What is PentAGI good for?
- Running automated security tests on systems you are authorized to test, scanning hosts and services for vulnerabilities with common security tools, writing vulnerability reports with exploitation guides, and keeping test findings and past approaches for later testing.
Similar agents
- FrontierAgent
FrontierAgent is an agent app that runs research and file-based work in a terminal, with one agent or a team of parallel sub-agents, for people comfortable with the command line.
- ResiMind
ResiMind is a framework that checks AI agent answers with independent verifiers and reuses checked rules for math and support tasks for developers building agents.
- Executioner
Executioner is a desktop app that runs AI agent teams and security tools for authorized penetration testing, keeping scope, targets, findings and evidence in one local workspace.
- TradingAgents
TradingAgents is a multi-agent framework that simulates a trading firm of LLM analysts, researchers, and managers to evaluate stock trades for researchers and developers.
- daily_stock_analysis
daily_stock_analysis is an agent app that runs daily AI analysis of stocks and sends decision dashboards to chat apps for individual investors.
- BettaFish
BettaFish is a self-hosted multi-agent system that analyzes public opinion across social media platforms and writes research reports for business decisions.