jy-666-yinzi/strix-kali-ai-poweredpentestframework — explained in plain English
Analysis updated 2026-05-18
Set up an autonomous AI pentesting agent on a Kali Linux machine.
Automatically scan a target for open ports and running services.
Generate and run proof-of-concept exploit scripts inside a safe Docker sandbox.
Connect the agent to different LLM providers based on cost or region.
| jy-666-yinzi/strix-kali-ai-poweredpentestframework | 0c33/agentic-ai | 0xbebis/hyperpay | |
|---|---|---|---|
| Stars | 14 | 14 | 14 |
| Language | — | Python | TypeScript |
| Setup difficulty | hard | hard | hard |
| Complexity | 4/5 | 4/5 | 5/5 |
| Audience | researcher | developer | developer |
Figures from each repo's GitHub metadata at analysis time.
Requires Kali Linux, Docker, and an API key for a supported LLM provider.
This repository is a deployment and configuration guide for Strix, an autonomous AI agent designed to perform security testing that mimics the actions of a real hacker. Rather than being the Strix tool itself, this project documents how to set it up and run it specifically on Kali Linux, a Linux distribution built for security work. According to the README, Strix can scan networks and identify open ports and running services automatically, attempt to get past web application firewalls and other defensive systems using analysis techniques, look for issues like insecure direct object references and flaws in application logic on endpoints that require login, and generate small scripts to prove a vulnerability is real, then run them inside an isolated Docker sandbox so nothing touches a live system by accident. The guide also explains how to connect Strix to several different large language model providers, including DeepSeek, Claude, Volcano Engine, and OpenRouter, letting a user pick whichever service fits their budget or region. It includes notes aimed at users in mainland China who have run into slow or stalled Docker sandbox downloads, along with steps meant to speed that process up. There is also a section on using an --instruction flag to give the AI agent more specific direction during a test. The README is written mostly for readers who already have some familiarity with Kali Linux and command line tools, and setup starts with installing Python 3 and its virtual environment tools through apt. The project includes a clear warning that Strix runs and executes generated proof-of-concept code automatically, so it should only be pointed at systems the user is authorized to test, never at systems belonging to someone else without permission. Because Strix performs real, automated exploitation attempts, this project is intended for security researchers and penetration testers rather than casual users or complete beginners to security work.
A setup and configuration guide for Strix, an autonomous AI agent that scans, tests, and exploits security vulnerabilities like a real hacker on Kali Linux.
The README does not state license terms.
Setup difficulty is rated hard, with roughly 1h+ to a first successful run.
Mainly researcher.
This repo across BitVibe Labs
Don't trust strangers blindly. Verify against the repo.