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.
MARK XXXIX-OR represents the pinnacle of the Jarvis series, evolving into a more flexible and robust system. It bridges the gap between the operating system and human intent. Through natural dialogue, Mark 39 analyzes your screen, processes uploaded documents, and executes complex workflows with a brand-new, adaptive interface.
It's not just an assistant — it's an extension of your digital life.
| 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 |
- 📂 Advanced File Handling — New support for direct file uploads. Drop PDFs, source code, or images into the assistant to have them analyzed, summarized, or edited instantly.
- 🎨 Adaptive & Flexible UI — A complete overhaul of the interface. The new UI is fully resizable and responsive, featuring transparency controls and customizable layouts to fit your workspace perfectly.
- 🐧🍎 Refined Cross-Platform Stability — Major fixes for macOS and Linux compatibility. Core system actions are now more consistent across all three major operating systems.
- ⚡ Optimized Core Engine — Significant performance boost in tool-calling logic and response generation, resulting in a 40% faster interaction speed.
- 🔀 OpenRouter Integration — Selected action modules (web search, memory, flight finder, desktop control, and more) now route their LLM calls through OpenRouter's free-tier models. This significantly increases the effective request limit without any additional cost, while Gemini Live continues to handle real-time voice and tool-calling.
git clone https://github.com/FatihMakes/Mark-XXXIX-OR.git
cd Mark-XXXIX-OR
pip install -r requirements.txt
playwright install
python main.py
⚠️ Installation Note: To keep the repository lightweight, some OS-specific dependencies are not bundled inrequirements.txt. If you run into aModuleNotFoundError, simply install the missing package viapip install <module_name>for your specific system.
| Requirement | Details |
|---|---|
| OS | Windows 10/11, macOS, or Linux |
| Python | 3.11 or 3.12 |
| Microphone | Required for voice interaction |
| API Keys | Free Gemini API key + Free OpenRouter API key |
Personal and non-commercial use only. Licensed under Creative Commons BY-NC 4.0.
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 |
| @fatihmakes |