An open-source AI penetration testing tool that uses autonomous AI hackers to dynamically run code, discover vulnerabilities, and validate them with real, exploitable PoCs.
- v1.7.1
- Published at
- 2d ago
- 74,987
- Stars
- 114,100
- Download
- Synced at
- 2d ago
Latest release
v1.7.1Nov 10, 2026, 09:24 PMDownloads slow? Switch the source anytime above
README
Project Overview
Strix is an open-source AI penetration testing tool that uses autonomous AI hackers to dynamically run your code, find vulnerabilities, and validate them through actual proofs-of-concept. It is built for developers and security teams who need fast, accurate security testing without the overhead of manual pentesting or the false positives of static analysis tools.
Key Features
- Full pentesting toolkit: reconnaissance, exploitation, and validation out of the box
- Multi-agent orchestration: teams of AI pentesters that collaborate and scale
- Real exploit validation: working PoCs, not false positives
- Developer-first CLI: actionable findings with remediation guidance
- Auto-fix & reporting: generate patches and compliance-ready pentest reports
- CI/CD integration: automatically scan on every PR and block insecure code
Target Audience
- Developers who need fast security testing
- Security teams and penetration testers
- DevOps and DevSecOps engineers
Quick Start
- Install Strix:
curl -sSL https://strix.ai/install | bash - Configure your AI provider:
export STRIX_LLM="openai/gpt-5.4"andexport LLM_API_KEY="your-api-key" - Run your first security assessment:
strix --target ./app-directory - Use from your coding agent:
npx skills add usestrix/strix
Core Advantages
- Autonomous AI hackers that behave like real hackers
- Real PoCs instead of false positives
- One-click autofix with ready-to-merge PRs
- CI/CD integration to block insecure code in PRs
System Requirements
- OS: Cross-platform (requires Docker runtime)
- Additional Dependencies: Docker (running), LLM API key
Release history
Sort