Summary

FatihMakes/Mark-XXXIX-OR provides a cross-platform, local-execution personal AI assistant designed to integrate deeply with a user's computer. It aims to act as an extension of the user's digital life by understanding and acting upon voice commands, visual input, and uploaded documents, offering a subscription-free, autonomous experience across Windows, macOS, and Linux.

How It Works

This project implements a real-time voice AI capable of ultra-low latency conversation, system control (launching apps, managing files, executing terminal commands), and autonomous task planning. It features visual awareness through real-time screen processing and webcam vision, persistent memory for context, and hybrid input modes. A novel adaptive UI offers resizable and customizable layouts, while advanced file handling allows direct analysis of uploaded PDFs, code, or images. LLM calls for certain modules are routed via OpenRouter's free tier to maximize request limits without cost, complementing Gemini Live for core voice and tool execution.

Quick Start & Requirements

• Install: Clone the repository, install dependencies with pip install -r requirements.txt, install Playwright with playwright install, and run python main.py.
• Prerequisites: Windows 10/11, macOS, or Linux; Python 3.11 or 3.12; Microphone; Free Gemini API key; Free OpenRouter API key.
• Notes: OS-specific dependencies may require manual pip install <module_name> if ModuleNotFoundError occurs.

Highlighted Details

• Advanced File Handling: Supports direct upload and analysis of PDFs, source code, and images.
• Adaptive UI: Fully resizable and responsive interface with transparency and customizable layouts.
• Cross-Platform Stability: Significant improvements for macOS and Linux compatibility.
• Optimized Core Engine: Achieves a 40% faster interaction speed.
• OpenRouter Integration: Extends LLM request limits cost-free by routing specific module calls.

Maintenance & Community

The project is engineered by FatihMakes, who shares updates and content via YouTube (@FatihMakes) and Instagram (@fatihmakes). No specific community channels (e.g., Discord, Slack) or roadmap links are provided in the README.

Licensing & Compatibility

Licensed under Creative Commons BY-NC 4.0, this software is strictly for personal and non-commercial use. Commercial adoption or linking with closed-source projects is prohibited by the license terms.

Limitations & Caveats

The installation process may require manual installation of OS-specific Python packages not included in the main requirements file. The Creative Commons BY-NC 4.0 license explicitly prohibits commercial use.