Jarvis-Model 🤖

A premium, modular AI assistant with a futuristic HUD interface, advanced automation skills, and living responsiveness.

---

✨ Overview

Jarvis-Model is a voice-controlled AI assistant that blends a stunning "Starark‑style" HUD with powerful automation capabilities. Built in Python using PyQt6 for the GUI and Groq's LLM engine for natural language understanding, Jarvis offers both voice and text modes, making it suitable for any environment.

The assistant is designed around a modular skill system—new capabilities can be dropped into the skills/ directory and are instantly available.

---

🚀 Core Features

• Futuristic HUD
  • Animated Arc Reactor core that pulses with voice activity
  • Dynamic Hexagon Panel background visualizations
  • Real‑time Telemetry bars for system feedback
• Dual Interaction Modes
  • Voice Mode: Hands‑free interaction via speech recognition & TTS
  • Text Mode: Silent CLI for debugging or quiet environments
• Modular Skill Architecture
  • Drop‑in skill modules in skills/
  • Easy extension without touching core code
• Rich Skill Set
  • Web & communication (Google search, WhatsApp, Email)
  • Vision & sensing (YOLO object detection, camera, screenshot, Gemini Live)
  • System control (volume, brightness, app management, file ops)
  • Context awareness (date/time, long‑term memory)

---

📦 Installation

Prerequisites

• Python 3.10+
• A Groq API Key (free tier available)
• Git (to clone the repository)

Steps

1. Clone the repository

   git clone https://github.com/RagaviDevX/Jarvis-Model.git
   cd Jarvis-Model

2. Install dependencies

   pip install -r requirements.txt

   Note: The project relies on PyQt6 for the GUI and ultralytics for vision.

3. Configure environment Create a .env file in the project root:

   GROQ_API_KEY=your_groq_key_here
   # Add additional keys as required by specific skills (e.g., WhatsApp, Email)

4. Launch the assistant

   • Voice mode (with GUI)

     python main.py

   • Text‑only mode

     python main.py --text

---

📂 Project Structure

Jarvis-Model/
├── Project_JARVIS-main/   # Core source code (kept for legacy compatibility)
│   ├── core/              # Engine, voice processing, skill registry
│   ├── gui/               # PyQt6 application logic & rendering
│   ├── skills/            # Individual capability modules
│   ├── assets/            # Images, icons, arc reactor graphics
│   ├── requirements.txt   # Python dependencies
│   └── main.py            # Entry point
├── .env                   # Environment variables (create from .env.template)
├── README.md              # This file
└── .gitignore

Tip: The actual runnable code lives inside Project_JARVIS-main/. The top‑level folder is kept clean for GitHub presentation.

---

🛠️ Available Skills

Category	Skill	Description
Web & Communication	web_ops	Google search & website opening
	whatsapp_skill	Automated WhatsApp messaging via Selenium
	email_ops	Send, read, and manage emails
Vision & Sensing	detection_skill	Real‑time object detection (YOLOv8)
	camera_skill	Capture photos & process visual input
	screenshot_ops	Take & analyze screenshots
	gemini_live_skill	Advanced multimodal interaction
System Control	system_ops	Volume, brightness, app management
	file_ops	Create, read, organize files
	memory_ops	Long‑term memory & context awareness
	datetime_ops	Date & time utilities
Text	text_ops	Text manipulation & processing
Weather	weather_ops	Fetch weather information

Skills are auto‑loaded from the skills/ directory. To add a new skill, create a Python file following the existing template and register it in core/registry.py.

---

▶️ Usage Examples

Voice Interaction

1. Run python main.py.
2. The HUD appears with a pulsating Arc Reactor.
3. Speak naturally—e.g., “What’s the weather today?” or “Open YouTube.”
4. Click the reactor to pause/resume listening.

Text Interaction

python main.py --text
> What is the capital of Japan?
> Tokyo is the capital of Japan.
>

Debugging

• Use --text mode to see logs directly in the terminal.
• Individual skills can be tested by importing them in a Python REPL.

---

🤝 Contributing

We welcome contributions! Please follow these steps:

1. Fork the repository.
2. Create a feature branch (git checkout -b feature/amazing-skill).
3. Commit your changes (git commit -m 'Add amazing skill').
4. Push to the branch (git push origin feature/amazing-skill).
5. Open a Pull Request.

Please ensure:

• Code follows PEP 8 (we use ruff for linting).
• New skills include a short docstring and are placed in skills/.
• Update README.md if you add new major features.

---

📜 License

This project is licensed under the MIT License – see the LICENSE file for details.

---

🙋‍♂️ Support & Contact

• Author: Ragavi DevX
• GitHub: @RagaviDevX
• Questions? Open an issue or drop a message in the Discussions tab.

---

Jarvis-Model – Your intelligent companion, ready to assist with voice, vision, and automation.
Built with ❤️ using Python, PyQt6, and Groq.