An advanced AI Online Playground for Tailwind CSS, Avoid sending useless messages to the AI agent.
# AI Tailwind Playground An advanced AI-powered online playground for Tailwind CSS, built for [Bardui.com](https://bardui.com). This interactive development environment allows you to generate and preview Tailwind CSS components in real-time using AI. ## Features - **AI-Powered Component Generation**: Ask the AI to create Tailwind CSS components using natural language - **Live Preview**: See your components render instantly in a side-by-side preview pane - **Monaco Editor**: Professional code editing experience with syntax highlighting - **Real-time Updates**: Changes in the editor are immediately reflected in the preview - **Tailwind CSS v4**: Powered by the latest Tailwind CSS browser runtime ## How It Works 1. Type your request in the search input (e.g., "create a tailwind card component") 2. The AI generates HTML code with Tailwind CSS classes 3. The code appears in the Monaco editor on the left 4. The live preview on the right shows the rendered component instantly 5. Edit the code manually or ask for more changes ## Tech Stack - **Next.js 15** - React framework - **Monaco Editor** - VS Code's editor component - **AI SDK** - Vercel AI SDK for streaming responses - **DeepSeek** - AI model integration - **Tailwind CSS v4** - Utility-first CSS framework ## Getting Started 1. Clone the repository 2. Install dependencies: ```bash npm install ``` 3. Set up your environment variables: Create a `.env.local` file and add your Claude API key: ``` DEEPSEEK_API_KEY=your_api_key_here ``` 4. Run the development server: ```bash npm run dev ``` 5. Open [http://localhost:3000](http://localhost:3000) in your browser ## Project Structure ``` ├── src/ │ ├── app/ │ │ ├── api/chat/ # API route for AI chat │ │ ├── chat/ # Chat page component │ │ └── page.tsx # Main playground page │ └── components/ │ └── search-input.tsx # AI input component ``` ## Usage Tips - Be specific in your reques
HAL 分层混合模型工作流 — 强模型(Claude)负责理解/拆解/验收,低成本模型(DeepSeek)负责检索/提取/清洗。Hermes Agent skill。
An LLM agent fine-tuned on DeepSeek for spaced repetition, dynamically integrating knowledge points based on the Ebbinghaus forgetting curve.
基于 STM32F103 构建的端到端 AI 智能手表生态。自研“零重定位”原生机器码动态加载引擎与页面栈式 UI 框架;集成生产级 OTA 回滚保护机制与高带宽(921600 baud)串口协议栈。通过 Node.js 中继实现 DeepSeek AI 语义控制及 ASRPRO 语音全双工交互,是一个集成了分布式计算、现代存储管理与 AI Agent 的嵌入式全栈工程。
A Meta-Agent-Driven Self-Evolving Multi-Agent System for UAV Detection and Tracking
One command to run Hermes AI Agent with a browser UI. Zero prerequisites. 一行命令,AI 就位。
网页应用Agent,接入DeepSeek、Mimo等模型