RamiGPT is an AI-powered agent designed for automated privilege escalation in cybersecurity. It targets security professionals and researchers seeking to streamline the process of identifying and exploiting privilege escalation vulnerabilities on Linux and Windows systems. The agent leverages AI to analyze system configurations and execute relevant tools, aiming to achieve root access efficiently.

How It Works

RamiGPT integrates with offensive security tools like PwnTools and OpwnAI, along with enumeration scripts such as BeRoot and LinPEAS. It uses an AI model to interpret the output from these tools, identify potential privilege escalation vectors, and suggest or execute appropriate actions. This AI-driven approach aims to automate the decision-making process typically performed by human penetration testers.

Quick Start & Requirements

• Docker: git clone https://github.com/M507/RamiGPT.git && cd RamiGPT && docker compose up -d
• Local: Requires Python 3, pip, and an OpenAI API key. Run ./generate_certs.sh, pip3 install -r requirements.txt, then python3 app.py.
• Prerequisites: OpenAI API key, Docker (for Docker install), Python 3.
• Access: Application available at https://127.0.0.1:5000.

Highlighted Details

• Achieved root access on multiple VulnHub systems in under a minute.
• Integrates BeRoot (Windows) and LinPEAS (Linux) for enumeration.
• Automates the analysis of enumeration tool outputs via AI.

Maintenance & Community

No specific details on contributors, sponsorships, or community channels (Discord/Slack) are provided in the README.

Licensing & Compatibility

The README does not specify a license. Compatibility for commercial use or closed-source linking is not mentioned.

Limitations & Caveats

RamiGPT requires an OpenAI API key, incurring costs associated with API usage. The project is intended for educational and authorized testing purposes only, and its effectiveness may vary depending on the target system's complexity and specific vulnerabilities.