--- title: SIFA Classification Agentic RAG Frontend emoji: 🤖 colorFrom: blue colorTo: purple sdk: docker app_port: 7860 pinned: false license: mit --- # Agent UI A modern chat interface for AI agents built with Next.js, Tailwind CSS, and TypeScript. This template provides a ready-to-use UI for interacting with Agno agents. agent-ui ## Features - 💬 **Modern Chat Interface**: Clean design with real-time streaming support - 🧩 **Tool Calls Support**: Visualizes agent tool calls and their results - 🧠 **Reasoning Steps**: Displays agent reasoning process (when available) - 📚 **References Support**: Show sources used by the agent - 🖼️ **Multi-modality Support**: Handles various content types including images, video, and audio - 🎨 **Customizable UI**: Built with Tailwind CSS for easy styling - 🧰 **Built with Modern Stack**: Next.js, TypeScript, shadcn/ui, Framer Motion, and more ## Getting Started ### Prerequisites Before setting up Agent UI, you may want to have an Agno Playground running. If you haven't set up the Agno Playground yet, follow the [official guide](https://agno.link/agent-ui#connect-to-local-agents) to run the Playground locally. ### Installation ### Automatic Installation (Recommended) ```bash npx create-agent-ui@latest ``` ### Manual Installation 1. Clone the repository: ```bash git clone https://github.com/agno-agi/agent-ui.git cd agent-ui ``` 2. Install dependencies: ```bash pnpm install ``` 3. Start the development server: ```bash pnpm dev ``` 4. Open [http://localhost:3000](http://localhost:3000) with your browser to see the result. ## Connecting to an Agent Backend By default Agent UI connects to `http://localhost:7777`. You can easily change this by hovering over the endpoint URL and clicking the edit option. The default endpoint works with the standard Agno Playground setup described in the [official documentation](https://agno.link/agent-ui#connect-to-local-agents). ## Contributing Contributions are welcome! Please see [CONTRIBUTING.md](./CONTRIBUTING.md) for contribution guidelines. ## License This project is licensed under the [MIT License](./LICENSE).