A modern, full-featured AI chat platform built with Next.js 14, featuring streaming responses, multiple AI providers, and a beautiful UI.
- 🤖 Multiple AI Provider Support
- Anthropic (Claude)
- OpenAI (GPT)
- Google (Gemini)
- 🌊 Streaming Responses
- Real-time message streaming
- Typing indicators
- Error handling
- 🎨 Modern UI/UX
- Responsive design
- Dark mode support
- Beautiful animations
- 🛠 Advanced Features
- PDF viewing capability
- Canvas drawing support
- Tool system integration
- 💼 Business Ready
- Landing page
- Pricing plans
- Testimonials
- Demo section
- Framework: Next.js 14 (App Router)
- Styling: Tailwind CSS
- Animations: Framer Motion
- AI Integration: Various AI Provider SDKs
- UI Components: Custom components with Tailwind
-
Clone the repository:
git clone https://github.com/yourusername/ai-chat-platform.git
-
Install dependencies:
npm install
-
Create a
.env.localfile with your API keys:ANTHROPIC_API_KEY=your_key_here OPENAI_API_KEY=your_key_here GOOGLE_API_KEY=your_key_here
-
Run the development server:
npm run dev
-
Open http://localhost:3000 in your browser.
├── app/
│ ├── page.tsx # Landing page
│ ├── chat/
│ │ └── page.tsx # Chat demo page
│ └── api/ # API routes
├── components/ # React components
├── lib/ # Utility functions
├── types/ # TypeScript types
└── public/ # Static assets
Required environment variables:
ANTHROPIC_API_KEY: Your Anthropic API keyOPENAI_API_KEY: Your OpenAI API keyGOOGLE_API_KEY: Your Google AI API key
Optional environment variables:
NEXT_PUBLIC_DEFAULT_PROVIDER: Default AI providerNEXT_PUBLIC_MAX_TOKENS: Maximum tokens per responseNEXT_PUBLIC_TEMPERATURE: Response temperature
- Fork the repository
- Create your 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
This project is licensed under the MIT License - see the LICENSE file for details.
- Next.js team for the amazing framework
- Vercel for the hosting platform
- AI providers for their powerful APIs
We've created a global dump command that can be used to create smart, token-aware dumps of any codebase. The script:
- Intelligently samples code based on importance
- Maintains token budgets
- Preserves critical sections like imports and types
- Keeps a history of recent dumps
The script is stored centrally at:
~/bin/scripts/codebase/concat_codebase.py~/bin/scripts/codebase/dump.sh
Usage: Simply run dump in any project directory.