A real-time voice AI that can hear, see, understand, and control your computer — on any OS. Supporting Windows, macOS, and Linux. Built with Gemini integration for maximum stability and performance, delivering zero subscriptions and total digital autonomy.

✨ Overview

MARK XLVI represents a massive milestone in the Jarvis series, evolving into a fully connected, highly persistent, and remote-accessible system. It completely bridges the gap between your mobile device, desktop OS, and human intent. Through real-time Gemini reasoning, Mark 46 allows you to control your PC from your phone, share large files securely, and maintain deep contextual conversations across sessions.

It's not just an assistant — it's an extension of your digital life.

🚀 Capabilities

Core Features

Feature	Description
🎙️ Real-time Voice	Ultra-low latency conversation in any language
🖥️ System Control	Launch apps, manage files, execute terminal commands
🧩 Autonomous Tasks	High-level planning for complex, multi-step goals
👁️ Visual Awareness	Real-time screen processing and webcam vision
🧠 Persistent Memory	Deeply remembers your projects, preferences, and personal context
⌨️ Hybrid Input	Seamlessly switch between keyboard typing and voice commands

🆕 What's New in XLVI

📱 Full Remote Phone Control — Take command of your entire desktop operating system directly from your smartphone, anywhere, anytime.
🧠 Advanced Long-Term Memory — Upgraded memory architecture allows Jarvis to contextually remember past interactions, preferences, and complex workflows across reboots.
🚀 Powered by Gemini Integration — Re-engineered from the ground up to utilize the full speed and precision of the Google Gemini API for ultimate reasoning and stability.
⚡ Next-Gen Performance & Stability — Comprehensive system-wide optimizations delivering faster response times and rock-solid execution on Windows, Mac, and Linux.
📂 Advanced File Handling & Hybrid Input — Fluidly switch between voice or keyboard input, and drag-and-drop code, PDFs, or images for instant analysis and automation.
🔒 Secure Mobile File Sharing — Wirelessly and securely share files or entire folders up to 500 MB from your phone directly to your computer with complete privacy.

⚡ Quick Start

git clone [https://github.com/FatihMakes/Mark-XLVI.git](https://github.com/FatihMakes/Mark-XLVI.git)
cd Mark-XLVI
pip install -r requirements.txt
playwright install
python main.py

⚠️ Installation Note: To keep the repository lightweight, some OS-specific dependencies are not bundled in requirements.txt. If you run into a ModuleNotFoundError, simply install the missing package via pip install <module_name> for your specific system.

📋 Requirements

Requirement	Details
OS	Windows 10/11, macOS, or Linux
Python	3.11 or 3.12
Microphone	Required for voice interaction
API Key	Free Gemini API key

⚠️ License

Personal and non-commercial use only. Licensed under Creative Commons BY-NC 4.0.

👤 Connect with the Creator

Engineered by a developer building a real-world JARVIS-style assistant. ⭐ Star the repository to support the journey to Mark 100.

Platform	Link
YouTube	@FatihMakes
Instagram	@fatihmakes