The Open Source ChatGPT Alternative - Bring Your Own API Key
🎯 Mission: Make AI accessible to everyone by providing a free, open-source ChatGPT interface where users control their own API keys and data.
OpenGPT's clean and intuitive interface - bringing the power of ChatGPT with complete privacy and control
- 💬 ChatGPT-like Interface - Familiar and intuitive chat experience
- 🔑 Bring Your Own API Key - No subscriptions, use your OpenAI credits directly
- 🧠 Intelligent Memory System - Advanced conversation context with 4-layer memory architecture
- 📱 Fully Responsive - Perfect experience on desktop, tablet, and mobile
- ⚡ Real-time Streaming - See responses as they're generated, just like ChatGPT
- 💾 Persistent Chat History - All conversations saved locally with full control
- 🗂️ Smart Chat Management - Organize with search, rename, delete, and auto-titles
- 🎯 4-Layer Architecture - Immediate, recent, historical, and important context layers
- 📊 Token Optimization - 85-90% token reduction for long conversations
- 🔄 Automatic Summarization - Intelligent compression of conversation history
- 💡 Context Preservation - Never lose important details from past messages
- ⚡ Infinite Scalability - Handle 500+ message conversations efficiently
- 🔐 Encrypted Local Storage - Your API keys are encrypted and stored locally
- 🚫 Zero Data Collection - We don't see, store, or analyze your conversations
- 🏠 Completely Local - All processing happens in your browser
- 🛡️ XSS Protection - Built-in security against common web vulnerabilities
- 🔒 No Server Logging - Your conversations never touch our servers
- 🌙 Beautiful Dark Theme - Sleek, modern design that's easy on the eyes
- 🎭 Smooth Animations - Polished micro-interactions throughout
- ⌨️ Keyboard Shortcuts - Power user friendly with Enter to send
- 📄 Markdown Support - Rich text rendering with code highlighting
- 📎 File Upload - Support for text, code, and document files
- 🎛️ Model Selection - Choose from GPT-4, GPT-3.5-turbo, and more
- 🔌 Model Context Protocol - Extend your agent with external tools and data sources
- 📡 Stdio Servers - Local servers accessed via command line (npx, node, python)
- 🌐 HTTP Servers - Remote or local servers with Streamable HTTP transport
- 🔑 Environment Variables - Configure API tokens and credentials securely
- 🛠️ Tool Discovery - Automatically discover and display available tools
- 👁️ Tool Visibility - See all tool calls in real-time with collapsible dropdowns
- ⚡ Persistent Connections - Servers connect once and stay alive
- 📊 Tool Results - View arguments, results, and visited URLs
- Node.js 18+ - Download here
- OpenAI API Key - Get yours here
- Clone the repository
git clone https://github.com/RaheesAhmed/OpenGPT.git
cd OpenGPT- Install dependencies
npm install
# or
yarn install
# or
pnpm install- Run the development server
npm run dev
# or
yarn dev
# or
pnpm dev-
Open your browser
Navigate to http://localhost:3000
-
Add your API key
Click the settings icon and securely add your OpenAI API key
That's it! Start chatting with AI while maintaining complete control over your data.
// Your API key workflow:
1. Enter API key in settings →
2. Encrypted with AES-256 →
3. Stored locally in browser →
4. Never sent to our servers →
5. Used directly with OpenAI API// 4-Layer Memory System:
Layer 1: Immediate Context (5-8 messages) // 800-1200 tokens
Layer 2: Recent Chunks (summarized) // 600-900 tokens
Layer 3: Historical Summary (compressed) // 400-600 tokens
Layer 4: Important Messages (preserved) // 200-400 tokens
Total: ~3k tokens (regardless of conversation length)// Local Browser Storage:
├── Encrypted API Keys
├── Chat Messages (by conversation ID)
├── Memory Context (intelligent summaries)
├── User Preferences
└── No server-side data (100% local)- Framework: Next.js 15+ (App Router)
- Language: TypeScript (Strict Mode)
- Styling: Tailwind CSS + shadcn/ui
- State Management: React Hooks + Local Storage
- Memory System: Custom intelligent context management
- Security: AES-256 encryption for API keys
- Deployment: Vercel-ready with Docker support
├── app/ # Next.js App Router
│ ├── api/ # API routes (chat, models)
│ ├── globals.css # Global styles
│ └── page.tsx # Main chat interface
├── components/ # React components
│ ├── ui/ # shadcn/ui components
│ ├── chat-sidebar.tsx # Chat management
│ ├── sidebar.tsx # Expanded sidebar
│ ├── mini-sidebar.tsx # Collapsed sidebar
│ └── model-selector.tsx # AI model selection
├── lib/ # Utility functions
│ ├── chat-memory.ts # Memory system
│ └── utils.ts # Helper functions
└── public/ # Static assets
All models from OpenAI are supported
const DEFAULT_CONFIG = {
model: "gpt-4o-mini",
temperature: 0.7,
streaming: true,
memoryEnabled: true,
autoTitle: true,
};- Click the button above
- Fork the repository
- Deploy automatically
- Start using immediately!
# Build for production
npm run build
# Start production server
npm start# Build the image
docker build -t opengpt .
# Run the container
docker run -p 3000:3000 opengptPerfect for complete privacy! Deploy on your own server:
# Clone and build
git clone https://github.com/RaheesAhmed/OpenGPT.git
cd OpenGPT
npm install
npm run build
# Run with PM2 (recommended)
pm2 start npm --name "opengpt" -- startWe welcome contributions! Here's how you can help:
Found a bug? Please create an issue with:
- Clear description of the problem
- Steps to reproduce
- Expected vs actual behavior
- Screenshots if applicable
Have an idea? We'd love to hear it! Please include:
- Clear description of the feature
- Use case and benefits
- Any implementation ideas
- Fork the repository
- Create a feature branch:
git checkout -b feature/amazing-feature - Make your changes
- Test thoroughly
- Commit with clear messages:
git commit -m 'Add amazing feature' - Push to your branch:
git push origin feature/amazing-feature - Open a Pull Request
- Use TypeScript for all new code
- Follow existing code style and patterns
- Add comments for complex logic
- Test your changes thoroughly
- Update documentation if needed
- 💬 GitHub Discussions: Ask questions & share ideas
- 🐛 Issues: Report bugs
- 📧 Email: [email protected]
❓ Is my API key safe? ✅ Yes! Your API key is encrypted and stored only in your browser. We never see it.
❓ Do you collect my conversations? ✅ No! All conversations stay on your device. Zero data collection.
❓ Can I use this offline? ❌ You need internet for API calls to OpenAI, but your data stays local.
❓ Which models are supported? ✅ All OpenAI models: GPT-4, GPT-4 Turbo, GPT-4o, GPT-3.5 Turbo, and more.
❓ Can I export my chats? ✅ Yes! Your chats are saved locally and can be backed up from browser storage.
❓ Is this really free? ✅ Completely free! You only pay OpenAI for your API usage.
| Feature | OpenGPT | ChatGPT Plus | Other Alternatives |
|---|---|---|---|
| Cost | Free + Your API | $20/month | Varies |
| Privacy | 100% Local | Data collected | Usually collected |
| API Key Control | You own it | N/A | Rarely |
| Customization | Full control | Limited | Limited |
| Open Source | ✅ MIT License | ❌ Closed | Rarely |
| Memory System | Advanced 4-layer | Basic | Basic |
| Self-Hosting | ✅ Yes | ❌ No | Rarely |
This project is licensed under the MIT License - see the LICENSE file for details.
- OpenAI - For the incredible GPT models
- Vercel - For Next.js and amazing deployment platform
- shadcn - For beautiful UI components
- The Open Source Community - For inspiration and contributions
Made with ❤️ by Rahees Ahmed
⭐ Star us on GitHub if you find this project useful!
"AI should be accessible to everyone, with complete privacy and control." - OpenGPT Mission
