A real-time voice AI that can hear, see, understand, and control your computer — on any OS. Supporting Windows, macOS, and Linux. Local execution. Zero subscriptions. Engineered for total autonomy.

✨ Overview

MARK XXXVII is the most versatile evolution of the Jarvis project. It transforms your operating system into a living, breathing intelligent entity. Through natural voice commands, Mark 37 analyzes your screen, manages your files, and executes complex workflows across different environments.

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
🔒 Privacy First	Physical mute button (F4 / UI) and fully local control
⌨️ Keyboard & Voice	Switch seamlessly between typing and speaking

🆕 What's New in XXXVII

🐧🍎 Cross-Platform Support (Experimental) — Now runs on Windows, macOS, and Linux. Core features work across all platforms; some OS-specific tasks may vary during the testing phase.
💤 Graceful Shutdown — Tell Jarvis to "Shut down" or "Close" and it exits the session properly.
🧠 Strengthened Memory — Improved long-term retention and context recall; better understanding of relationships and history.
🔧 Action Core Optimizations — Major bugs in action scripts fixed for smoother system execution.
⚡ Optimized Performance — Faster response times and refined tool-calling logic.

⚡ Quick Start

git clone https://github.com/FatihMakes/Jarvis-MK37.git
cd Jarvis-MK37
pip install -r requirements.txt
playwright install
python main.py

⚠️ Installation Note: Due to the new cross-platform integration, OS-specific libraries are not all bundled in requirements.txt to keep the install lightweight. If you encounter a ModuleNotFoundError, simply run 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 commands
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 an 18-year-old developer building a real JARVIS-style assistant. ⭐ Star the repository to support the journey to Mark 85.

Platform	Link
YouTube	@FatihMakes
Instagram	@fatihmakes