opentiny/tiny-robot

最近记录的来源活动: 2026年9月28日 01:09

SkillsMP 收录数据更新: 2026年11月5日 19:57

已收集 skills: 1

GitHub 星标: 101
GitHub Forks: 17

用 AI 助手安装

复制这段 Prompt，发给你正在使用的 AI 助手。

Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/opentiny/tiny-robot.

仓库 README

仓库 README 来源：README.md

查看 README 源文件

展开完整 README

<p align="center"> <a href="https://opentiny.design" target="_blank" rel="noopener noreferrer"> <img alt="OpenTiny Logo" src="https://raw.githubusercontent.com/opentiny/tiny-robot/HEAD/logo.svg" height="88" style="max-width:100%;"> </a> </p> <p align="center"> <a href="https://github.com/opentiny/tiny-robot"><img src="https://img.shields.io/github/stars/opentiny/tiny-robot" alt="GitHub stars"></a> <img src="https://img.shields.io/badge/License-MIT-yellow.svg" alt="MIT License"> <img src="https://img.shields.io/badge/Vue-3.x-42b883.svg" alt="Vue 3"> <img src="https://img.shields.io/badge/TypeScript-Ready-3178c6.svg" alt="TypeScript"> </p> English | [简体中文](https://github.com/opentiny/tiny-robot/blob/HEAD/README.zh-CN.md) **TinyRobot** is an AI component library and application development suite built with Vue 3 and following the OpenTiny Design system. It helps enterprises quickly build intelligent chat applications and business assistants. <p align="center"> <img src="https://raw.githubusercontent.com/opentiny/tiny-robot/HEAD/robot-highlights.gif" alt="TinyRobot MCP tool calls and Skill extensions demo" width="1100"> </p> ## ✨ Core Capabilities Core capabilities span the Chat suite, composable components, the data layer, and MCP extensions: - **Chat suite**: Provides a complete chat interface with model service integration, messaging, streaming responses, and management of multiple conversations, plus theme customization and model switching. - **Composable architecture**: Use Components and Kit to control the interface, runtime, message requests, and conversation data as needed. - **Tools and MCP**: Supports tool call display, MCP server management, tool selection, and approval workflows. - **Vue 3 + TypeScript**: Follows the OpenTiny Design system, with support for importing only what you need, theme customization, and typed APIs for extensions. ## 🧭 Capability Overview <p align="center"> <img src="https://raw.githubusercontent.com/opentiny/tiny-robot/HEAD/robot-panorama.png" alt="TinyRobot product capability overview" width="1100"> </p> Combine TinyRobot's capabilities as needed, from project setup and chat interfaces to business extensions. ## 🚀 How to Use TinyRobot offers three ways to get started: use the CLI, install the complete Chat suite, or combine Components and Kit as needed. ### Package Overview TinyRobot separates project setup, chat pages, UI components, and the data layer into public packages that can be used independently: | Package | Description | Version | | --- | --- | --- | | [`@opentiny/tiny-robot`](https://www.npmjs.com/package/@opentiny/tiny-robot) | AI chat component library with Bubble, Sender, History, Layout, and more | [![npm version](https://img.shields.io/npm/v/@opentiny/tiny-robot.svg)](https://www.npmjs.com/package/@opentiny/tiny-robot) | | [`@opentiny/tiny-robot-chat`](https://www.npmjs.com/package/@opentiny/tiny-robot-chat) | Chat suite with a complete chat page, runtime, conversation management, and MCP support | [![npm version](https://img.shields.io/npm/v/@opentiny/tiny-robot-chat.svg)](https://www.npmjs.com/package/@opentiny/tiny-robot-chat) | | [`@opentiny/tiny-robot-kit`](https://www.npmjs.com/package/@opentiny/tiny-robot-kit) | AI chat toolkit for message management, model service integration, multiple conversations, and data storage | [![npm version](https://img.shields.io/npm/v/@opentiny/tiny-robot-kit.svg)](https://www.npmjs.com/package/@opentiny/tiny-robot-kit) | | [`@opentiny/tiny-robot-cli`](https://www.npmjs.com/package/@opentiny/tiny-robot-cli) | CLI for creating projects or adding Chat to an existing Vue project | [![npm version](https://img.shields.io/npm/v/@opentiny/tiny-robot-cli.svg)](https://www.npmjs.com/package/@opentiny/tiny-robot-cli) | | [`@opentiny/tiny-robot-svgs`](https://www.npmjs.com/package/@opentiny/tiny-robot-svgs) | SVG icon library for TinyRobot components | [![npm version](https://img.shields.io/npm/v/@opentiny/tiny-robot-svgs.svg)](https://www.npmjs.com/package/@opentiny/tiny-robot-svgs) | ### 1. Get Started with the CLI #### Create a New Project Use the CLI to create a Vue project with Chat capabilities: ```bash npx @opentiny/tiny-robot-cli create my-app --template basic cd my-app pnpm install pnpm dev ``` #### Add Chat to an Existing Vue Project ```bash npx @opentiny/tiny-robot-cli add chat ``` The CLI generates `src/tiny-robot-chat/TinyRobotChat.vue` and related configuration. It does not automatically modify `App.vue`, `src/main.*`, or `vite.config.*`, or mount the component. See the [CLI integration guide](https://docs.opentiny.design/tiny-robot/guide/cli-integration) for more options and integration details. ### 2. Use the Complete Chat Suite For a complete Chat application, install: ```bash pnpm add @opentiny/tiny-robot @opentiny/tiny-robot-chat ``` Create a chat page with `TrChat` and `useChatRuntime`: ```vue <script setup lang="ts"> import '@opentiny/tiny-robot/dist/style.css' import '@opentiny/tiny-robot-chat/dist/style.css' import { TrChat, useChatRuntime, type ChatProviderConfig } from '@opentiny/tiny-robot-chat' const modelProviders: ChatProviderConfig[] = [ { type: 'openai', apiUrl: '/api/chat', models: [{ id: 'deepseek-flash', label: 'DeepSeek Flash' }], }, ] const runtime = useChatRuntime({ modelProviders }) </script> <template> <tr-chat :runtime="runtime" /> </template> ``` Replace `apiUrl` with your model service URL or a backend endpoint that forwards requests to the model service. The endpoint must use a format compatible with OpenAI's chat API. If you already have your own request and data layers, use `TrChatUI` to integrate just the Chat interface. ### 3. Compose Your Own Chat Application #### Components `@opentiny/tiny-robot` provides the basic components for AI chat interfaces, which you can combine to build your own pages: - Messages and input: `TrBubble`, `TrBubbleList`, `TrSender`, `TrSenderCompat` - Page structure and extensions: `TrLayout`, `TrContainer`, `TrHistory`, `TrPrompts`, `TrAttachments`, `TrMcpServerPicker` #### Kit `@opentiny/tiny-robot-kit` provides message processing, model requests, and conversation management for AI chat applications. Use it with TinyRobot components or your own interface: - `useMessage`: Manages message state and handles streaming responses. - `useConversation`: Manages multiple conversations and their messages. - Conversation storage: Supports LocalStorage, IndexedDB, and custom storage strategies. - Custom requests: Connects to model services or business APIs through `responseProvider`. ## 📚 Documentation and Examples - [Full Documentation](https://docs.opentiny.design/tiny-robot/) - [Quick Start](https://docs.opentiny.design/tiny-robot/guide/quick-start) - [CLI Integration](https://docs.opentiny.design/tiny-robot/guide/cli-integration) - [Chat Suite](https://docs.opentiny.design/tiny-robot/suites/quick-start) - [Chat Example](https://docs.opentiny.design/tiny-robot/examples/chat-tiny-robot) ## 🛠️ Development ```bash # Install dependencies pnpm install # Start development server pnpm dev # Run tests pnpm test # Build pnpm build ``` ## 📄 License MIT License - see [LICENSE](https://github.com/opentiny/tiny-robot/blob/HEAD/LICENSE) file for details. ## 🤝 Contributing Contributions are welcome! Please read our [Contributing Guide](https://github.com/opentiny/tiny-robot/blob/HEAD/CONTRIBUTING.md) to understand the recommended workflow, commit message conventions, and how to submit Issues and Pull Requests. ## 📞 Support - 📖 [Documentation](https://docs.opentiny.design/tiny-robot/) - 🐛 [Issue Tracker](https://github.com/opentiny/tiny-robot/issues) - 💬 [Discussions](https://github.com/opentiny/tiny-robot/discussions) ## 🙏 Acknowledgments Built with ❤️ by the OpenTiny team. --- **Note**: This project is part of the [OpenTiny](https://github.com/opentiny) ecosystem.

正在加载仓库 README…

这个仓库中的 skills

职业分类待补全

skill

职业分类

描述

更新

valid-skill

未分类

Skill package used by the SkillImportForm component contract test.

原文语言：英语

2026-09-28

已展示 1 / 1 个已收集 Skill。