Nat AI Personal Assistant 🤖

"Nat" is a sophisticated, always-on AI personal assistant that lives in a standalone Windows application. It controls your computer through voice commands and provides a premium desktop experience.

---

✨ Key Features

• 🎙️ Always-on Voice Processing: No wake words required after initialization. Nat listens, processes, and responds naturally.
• 🎩 Formal "Sir" Persona: A dedicated, professional assistant designed to treat you with executive respect.
• 🛠️ Deep System Integration: Nat can launch apps, search the web, manage files, type text, and even automate mouse clicks.
• 🧠 Multi-Provider Brain: Switch between OpenRouter (supports models like Nemotron-3), Google Gemini 1.5 Flash, or NVIDIA's Integrated API.
• 🖥️ Modern Desktop GUI: A stunning dark-themed interface built with CustomTkinter for real-time status and chat monitoring.
• 🔊 Voice Feedback: Local Text-to-Speech (TTS) integration using pyttsx3 for high-speed, offline voice output.

---

🛠️ Architecture

Nat is built on a modular, event-driven architecture that ensures reliability and extensibility.

graph TD
    A[User Voice] -->|SpeechRecognition| B(audio_handler.py)
    B -->|Transcribed Text| C(main.py)
    C -->|Command| D(brain.py)
    D -->|Tool Call| E(system_tools.py)
    E -->|Execute| F[Windows OS]
    D -->|AI Response| G(gui_app.py)
    G -->|Display| H[Desktop UI]
    D -->|AI Response| B
    B -->|TTS Output| I[User Audio]

Loading

---

🚀 Installation & Setup

Follow these steps to get Nat running on your Windows environment:

1. Prerequisites

• Python 3.11+ is highly recommended for compatibility with modern AI libraries.
• Git for repository management.

2. Clone and Install

git clone https://github.com/Shackey/Nat.git
cd Nat
pip install -r requirements.txt

3. Audio Support (Critical)

Nat requires PyAudio for voice features. If standard installation fails:

• Follow the troubleshooting guide in INSTALL.md

4. Configure Your Environment

Create a .env file from the example:

copy .env.example .env

Add your API keys and select your preferred provider:

PREFERRED_PROVIDER=openrouter  # Options: openrouter, google, nvidia
OPENROUTER_API_KEY=sk-or-v1-...
GOOGLE_API_KEY=...
NVIDIA_API_KEY=...

---

🎮 How to Use

Launching Nat

The easiest way to start is by using the provided batch file:

• Simply double-click run_nat.bat (or execute python gui_app.py).

Example Voice Commands

• "Nat, open Notepad and write a poem."
• "Nat, search the web for the latest NVIDIA GPU releases."
• "Nat, what is 45% of 125,000?"
• "Nat, please press Ctrl+S to save my work."
• "Nat, shutdown yourself."

---

📂 Project Structure

• gui_app.py: The primary interface for users to interact with Nat.
• brain.py: The "intelligence" layer handling LLM logic and function calling.
• audio_handler.py: Manages wake-word detection, STT (Speech-to-Text), and TTS (Text-to-Speech).
• system_tools.py: A robust library of tools Nat uses to control the OS.
• main.py: The central coordinator for voice-only logic.

---

🤝 Contributing

Contributions are what make the open-source community such an amazing place. Any contributions you make are greatly appreciated.

1. Fork the Project
2. Create your Feature Branch (git checkout -b feature/AmazingFeature)
3. Commit your Changes (git commit -m 'Add some AmazingFeature')
4. Push to the Branch (git push origin feature/AmazingFeature)
5. Open a Pull Request

📄 License

Distributed under the MIT License. See LICENSE for more information.