Data

Tools

Indexes

Applications

Experiments

Awesome

An open API service indexing awesome lists of open source software.

https://github.com/pkparthk/buddy-ai

Buddy AI is a full-stack, AI-powered personal assistant that combines voice recognition, natural language processing, and advanced command interpretation. Built with Python (Flask) and React (TypeScript), it features smart web navigation, real-time system monitoring, weather/news APIs, and context-aware responses.
https://github.com/pkparthk/buddy-ai

api artificial-intelligence flask gtts machine-learning python react reactjs rest-api speechrecognition tailwindcss typescript

Last synced: 6 months ago
JSON representation

Buddy AI is a full-stack, AI-powered personal assistant that combines voice recognition, natural language processing, and advanced command interpretation. Built with Python (Flask) and React (TypeScript), it features smart web navigation, real-time system monitoring, weather/news APIs, and context-aware responses.

Awesome Lists containing this project

README 

          
# 🤖 Buddy AI - Your Intelligent Personal Assistant



**Buddy AI** is an advanced full-stack AI-powered personal assistant that combines natural language processing and intelligent command interpretation. Built with Flask backend and React TypeScript frontend, it offers seamless voice interactions and smart automation capabilities.



## 🌟 Features



### 🎯 Core Capabilities



- **Voice Recognition & Speech Synthesis**: Natural voice interactions with gTTS (development mode)

- **Intelligent Command Processing**: Advanced pattern matching and AI-driven command interpretation

- **Dynamic Web Navigation**: Smart website opening with context-aware platform selection

- **Real-time System Monitoring**: CPU, memory, battery, and disk space monitoring using Psutil

- **AI-Powered Conversations**: Powered by Google Gemini AI for natural conversations

- **Production-Ready API**: Flask backend with CORS support and serverless deployment



### 🔧 Smart Command Categories



#### 🌐 Web & Search Intelligence



- **Smart Search**: Automatically chooses optimal platforms (YouTube, Google, Stack Overflow, GitHub)

- **Direct Website Access**: 30+ popular websites with intelligent URL resolution

- **Context-Aware Searches**: "Python tutorials" → YouTube, "JavaScript error" → Stack Overflow



#### 💻 System Control & Monitoring



- **Real-time System Information**: Battery, memory, CPU, and disk monitoring

- **Application Management**: Launch applications with smart detection

- **Cross-platform Support**: Windows, macOS, and Linux compatibility



#### 📊 External API Integration



- **Weather Services**: Real-time weather via OpenWeatherMap API (optional)

- **News Updates**: Latest news via News API integration (optional)

- **Mathematical Calculations**: Complex calculations and unit conversions



## 🏗️ Technical Architecture



### Backend (Flask API)



- **REST API**: Flask with CORS support and health monitoring endpoints

- **AI Integration**: Google Gemini AI for conversational capabilities

- **External APIs**: Weather, News, and location services (optional)

- **System Monitoring**: Real-time metrics using Psutil

- **Audio Processing**: gTTS for development environments (disabled in production)

- **Environment Management**: Production and development configurations



### Frontend (React TypeScript)



- **Modern UI**: React 18 with TypeScript and Tailwind CSS

- **Voice Interface**: Web Speech API integration for voice commands

- **Real-time Chat**: Interactive conversation interface with typing indicators

- **Responsive Design**: Mobile-first design with adaptive layouts

- **Quick Commands**: Pre-built shortcuts for common tasks



### Deployment



- **Backend**: Production-ready Flask app with serverless compatibility

- **Frontend**: Static build optimized for CDN deployment

- **Environment Configuration**: Separate dev/production settings



## 🛠️ Technology Stack



### Backend



- **Python 3.11+** with Flask 3.1.0

- **Google Generative AI** for Gemini integration

- **gTTS** for text-to-speech (development only)

- **Psutil** for system monitoring

- **Requests & BeautifulSoup** for web scraping

- **Flask-CORS** for cross-origin support



### Frontend



- **React 18** with TypeScript

- **Tailwind CSS** for styling

- **Vite** for build tooling and development server

- **Web Speech API** for voice recognition



### External Services



- **Google Gemini AI** (required)

- **OpenWeatherMap API** (optional)

- **News API** (optional)



## 🚀 Quick Start



### Prerequisites



- Python 3.8+

- Node.js 16+

- Google Gemini AI API Key



### Installation



1. **Clone the repository**



   ```bash

   git clone https://github.com/pkparthk/Buddy-AI.git

   cd Buddy-AI

   ```



2. **Set up the backend**



   ```bash

   # Install Python dependencies

   pip install -r requirements.txt



   # Create environment file

   cp .env.example .env

   ```



3. **Configure API Keys**

   Copy the example environment file and add your API keys:



   ```bash

   # Copy the template

   cp .env.example .env

   ```



   Edit `.env` file and add your API keys:



   ```env

   GEMINI_API_KEY=your_gemini_api_key_here

   OPENWEATHER_API_KEY=your_openweather_api_key_here  # Optional

   NEWS_API_KEY=your_news_api_key_here                # Optional

   FLASK_ENV=development

   ```



4. **Set up the frontend**

   ```bash

   cd my-app

   npm install

   ```



### Running the Application



1. **Start the backend server**



   ```bash

   python api.py

   ```



2. **Start the frontend (in a new terminal)**



   ```bash

   cd my-app

   npm run dev

   ```



3. **Access the application**

   Open your browser and go to `http://localhost:5173`



## 🎯 Usage Examples



### Voice Commands



```

"Hey Buddy, open YouTube"

"Search for machine learning tutorials"

"What's the weather in Mumbai?"

"Open Visual Studio Code"

"What's my battery level?"

"Calculate 25 * 67"

"Search Python error on Stack Overflow"

"Open GitHub and search React"

```



### System Monitoring



```

"Check CPU usage"

"What's my memory status?"

"Show disk space"

"Battery information"

```



### Web Navigation



```

"Open Gmail"

"Go to Facebook"

"Visit Instagram"

"Launch Netflix"

"Open Google Drive"

```



## 🛠️ API Configuration



### Required APIs



- **Google Gemini AI**: For natural language processing

  - Get your key at: https://makersuite.google.com/app/apikey



### Optional APIs



- **OpenWeatherMap**: For weather information

  - Get your key at: https://openweathermap.org/api

- **News API**: For news updates

  - Get your key at: https://newsapi.org/



## 📁 Project Structure



```

Buddy-AI/

├── api.py                        # Flask REST API server with CORS

├── main.py                       # Core voice processing and TTS logic

├── model.py                      # Enhanced Gemini AI integration

├── enhanced_commands.py          # Advanced command processing engine

├── external_apis.py              # Weather, news, and location APIs

├── requirements.txt              # Python dependencies

├── .env.example                  # Environment variables template

├── render.yaml                   # Render deployment configuration

├── COMPLETE_DEPLOYMENT_GUIDE.md  # Comprehensive deployment guide

├── DEPLOYMENT_CHECKLIST.md       # Deployment checklist

└── my-app/                       # React TypeScript frontend

    ├── src/

    │   ├── components/

    │   │   ├── BuddyAI.tsx       # Main AI interface component

    │   │   └── ui/               # Reusable UI components

    │   └── App.tsx               # Root React component

    ├── package.json              # Frontend dependencies

    ├── tailwind.config.js        # Tailwind CSS configuration

    ├── vite.config.ts            # Vite build configuration

    └── vercel.json               # Vercel deployment settings

```



## 🚀 Deployment



### Local Development



1. **Backend**: `python api.py` (runs on http://localhost:5000)

2. **Frontend**: `npm run dev` (runs on http://localhost:5173)



### Production Deployment



- **Backend**: Deploy to serverless platforms (Render, Railway, etc.)

- **Frontend**: Deploy to CDN platforms (Vercel, Netlify, etc.)



## 🤝 Contributing



We welcome contributions! Please:



1. Fork the repository

2. Create a feature branch (`git checkout -b feature/AmazingFeature`)

3. Commit your changes (`git commit -m 'Add AmazingFeature'`)

4. Push to the branch (`git push origin feature/AmazingFeature`)

5. Open a Pull Request



## 🎥 Demo



🎥 [Demo Video](https://vimeo.com/1078472414?share=copy) - See the complete voice interaction experience!



## 📝 License & Usage



This project is open source and available under the [MIT License](LICENSE). As a student project, feel free to use, modify, and learn from this code. If you use this project or parts of it, please provide attribution by linking back to this repository.



**Note**: This project uses external APIs (Google Gemini AI, OpenWeatherMap, News API) that may have their own terms of service and usage limits.



## 📞 Contact



- **Email**: [0xparthk@gmail.com](mailto:0xparthk@gmail.com)

- **GitHub**: [pkparthk](https://github.com/pkparthk)



---



**🚀 Transform your computer interaction with Buddy AI - Your intelligent personal assistant powered by cutting-edge AI technology!**



_Built with ❤️ by [Parth Kothari](https://github.com/pkparthk)_