Study Buddy AI is an intelligent, multi-modal academic assistant powered by advanced AI technology. It helps students learn more effectively by providing personalized explanations, processing various file formats, and offering interactive learning experiences.
Try it now: https://assassinaj602.github.io/study-buddy-ai/
- Intelligent Responses: Get personalized explanations tailored to your learning style
- Multi-Subject Support: Covers Math, Science, English, History, Computer Science, and more
- Grade-Level Adaptation: Adjusts complexity from Elementary to College level
- Multiple Learning Styles: Detailed, Summary, Funny, and Step-by-step explanations
- PDF Processing: Extract and analyze text from PDF documents
- Word Document Support: Process .docx files seamlessly
- Image OCR: Extract text from images using advanced OCR technology
- Voice Input: Record and transcribe speech to text
- Responsive Design: Works perfectly on desktop, tablet, and mobile devices
- Dark/Light Mode: Toggle between themes for comfortable viewing
- Interactive Elements: Smooth animations and hover effects
- Real-time Streaming: See AI responses as they're generated
- A modern web browser (Chrome, Firefox, Safari, Edge)
- Internet connection for AI API calls
- API key from OpenRouter AI (or compatible AI service)
-
Clone the repository
git clone https://github.com/assassinaj602/study-buddy-ai.git cd study-buddy-ai -
Open the project
- Simply open
index.htmlin your web browser - No build process required - it's a pure HTML/CSS/JavaScript application
- Simply open
-
Configure API Key
- Open
index.htmlin a text editor - Find the
API_KEYvariable and replace it with your OpenRouter AI API key
const API_KEY = 'your-api-key-here';
- Open
The application uses OpenRouter AI by default, but you can configure it to use other AI services:
// API Configuration
const API_KEY = 'your-api-key-here';
const API_URL = 'https://openrouter.ai/api/v1/chat/completions';- Select your subject, grade level, and preferred learning style
- Type your question in the text area
- Click "Send" or press Enter to get an AI response
- Use "Stop" to interrupt generation or "Remake" to get a different response
- PDF/Word Documents: Click "Upload File" and select your document
- Images: Click "Upload Photo" to process images with OCR
- Voice: Click "Record Voice" to convert speech to text
- Stop Generation: Interrupt long responses mid-stream
- Remake Answers: Get alternative explanations for the same question
- Theme Toggle: Switch between light and dark modes
- Responsive Design: Use on any device size
- Frontend: HTML5, CSS3, Vanilla JavaScript
- AI Integration: OpenRouter AI API
- File Processing:
- PDF.js for PDF processing
- Mammoth.js for Word documents
- Tesseract.js for OCR
- Speech Processing: Web Speech API & AssemblyAI
study-buddy-ai/
โโโ index.html # Main application file
โโโ README.md # This file
โโโ screenshots/ # Interface screenshots
โโโ main-interface.png
โโโ chat-interface.png
โโโ file-upload.png
โโโ dark-mode.png
โโโ basic-chat.png
โโโ file-processing.png
- Streaming Responses: Real-time AI response display
- File Processing: Multi-format document analysis
- OCR Integration: Image-to-text conversion
- Responsive Design: Mobile-first approach
- Dark Mode: CSS custom properties for theming
- Homework Help: Get explanations for difficult concepts
- Document Analysis: Process study materials and textbooks
- Note Taking: Convert handwritten notes to digital text
- Quick Quizzes: Generate practice questions from uploaded content
- Content Creation: Generate educational materials
- Student Assessment: Analyze student work and provide feedback
- Lesson Planning: Create structured learning content
- Accessibility: Convert various formats to accessible text
- No Data Storage: All processing happens in real-time
- Client-Side Processing: File processing occurs in your browser
- API Security: Uses secure HTTPS connections
- No Personal Data: Only chat content is sent to AI services
We welcome contributions! Here's how you can help:
- Fork the repository
- Create a feature branch
git checkout -b feature/amazing-feature
- Commit your changes
git commit -m 'Add some amazing feature' - Push to the branch
git push origin feature/amazing-feature
- Open a Pull Request
- Follow existing code style and formatting
- Test on multiple browsers and devices
- Update documentation for new features
- Keep the single-file architecture when possible
This project is licensed under the MIT License - see the LICENSE file for details.
- OpenRouter AI for providing the AI API
- PDF.js for PDF processing capabilities
- Tesseract.js for OCR functionality
- Mammoth.js for Word document processing
- AssemblyAI for speech-to-text services
- Material Icons for the beautiful icons
If you encounter any issues or have questions:
- Check the Issues: Look for existing solutions
- Create an Issue: Report bugs or request features
- Email Support: [email protected]
- Documentation: Check this README for detailed information
- Real-time collaboration features
- Extended file format support
- Custom AI model integration
- Progress tracking and analytics
- Mobile app development
- Multi-language support
- Advanced quiz generation
- Study session management
Made with โค๏ธ for students and educators worldwide
Last updated: July 2025






