- 团队里非工程背景的成员要独立做出一个带 LLM 调用的原型:这里的三阶段路径把 RAG、图像生成、Supabase/Stripe 串成一条线,比让他们自己在文档里拼凑要省事
- 需要给新人做 AI 应用开发的入门培训:交互演示和虚拟鼠标模拟 IDE 工作流,比纯文字教程更容易让人跑通第一遍
- 多语言团队或社区做本地化教学材料:仓库本身提供 10 种语言版本,省去自己翻译的成本
- 想快速了解一个 AI 产品从原型到上线的完整链路(含支付、后端):当作路线图读,而不是当作参考手册查
easy-vibe
datawhalechina活跃维护 有专家点评面向 AI 产品构建者的入门课程,教你用 Vibe Coding 方式借助 GPT、DeepSeek 等大模型和低代码工具快速做出产品。
💻 Vibe Coding 101|Your First Course For AI Product Builders.
专家点评
上手难度:入门更新于 2026-11-11面向零基础转 AI 产品构建的实战教程仓库,不是工具,顶替的是「从看文档到做出第一个能上线的 AI 应用」这段空白
适用场景
踩坑
- 把它当成可安装的软件或脚手架来 clone:这是教程仓库,README 明确说需要按在线教程逐步操作,本地运行方式在 Run Locally 章节,直接找 package.json 跑起来会扑空
- 内容仍在补全中:issue 里「催更」「添加新手快速开始指南」这类请求反复出现,说明部分章节和入门引导尚未完备,按目录推进时可能撞到未写完的部分
- 文档细节问题会被反复报:标题锚点错位、文本错误这类 issue 说明内容校对不是一次到位的,跟着链接跳转时可能定位不到预期位置
同类对比
如果目标是直接拿一个能跑的 AI 应用模板而不是学一遍,去看各框架官方的 starter 模板(如 Next.js AI Chatbot 模板)更直接;如果是要系统学 LLM 应用开发的理论与工程实践,这个仓库偏产品落地路径,深度上不如专门的课程或书籍。
README 里没有找到可直接复制的安装命令,请到 README 或官方文档查看安装方式。
README 未说明
项目说明
由 README 自动翻译提炼面向 AI 产品构建者的 Vibe Coding 实战教程,带你从零基础走到产品上线
面向 AI 产品构建者的入门课程,教你用 Vibe Coding 方式借助 GPT、DeepSeek 等大模型和低代码工具快速做出产品。
核心能力
- 按三阶段学习地图从零基础推进到产品上线
- 用交互演示讲清 RAG 数据流与 AI 生成图像原理
- 用虚拟鼠标引导模拟 IDE 核心工作流
- 覆盖全栈与跨平台项目实战,含 Supabase 与 Stripe 集成
- 教程内容提供 10 种语言版本
容易踩的坑
这是教程类仓库,不是可直接安装运行的软件,需按在线教程逐步操作;本地运行方式见 README 的 Run Locally 章节,具体命令未在可见部分给出
- v0.4.0Easy-Vibe Open Textbook v0.4.0最新正式版2026-08-07 · 2026-08-07 04:54 UTC
Easy-Vibe Open Textbook v0.4.0
This release adds offline editions of the Easy-Vibe open textbook in 10 languages, available as both PDF and EPUB. Each file covers Stages 1, 2 and 3 (all core chapters); appendix chapters are intentionally excluded to keep the downloads small.
Scope
- Stages 1, 2 and 3 only. All appendix content is omitted.
- Each book contains roughly 55 chapters, covering the complete path from AI product prototyping to full-stack development.
Languages
Code Language zh-cn简体中文 zh-tw繁體中文 enEnglish ja-jp日本語 ko-kr한국어 es-esEspañol fr-frFrançais de-deDeutsch vi-vnTiếng Việt ar-saالعربية (RTL) Downloads
20 assets are attached:
easy-vibe-open-textbook-<locale>-v0.4.0.{pdf,epub}.- PDF: A4, vector fonts, print-ready, clickable TOC. 39–48 MB per file.
- EPUB: EPUB3, reflowable, suitable for phones, e-readers and Apple Books. 58–67 MB per file.
- Arabic (
ar-sa) is typeset right-to-left via XeLaTeX with polyglossia.
PDF is recommended for desktop and printing; EPUB is recommended for mobile and e-ink readers.
Build
- PDF pipeline: XeLaTeX with per-locale font stacks, post-processed through Ghostscript (
/printer, 144 dpi bicubic downsampling, sRGB, font subsetting, duplicate-image deduplication). - EPUB pipeline: raster images resized to at most 1200 px on the longest edge; large PNGs converted to JPEG (q=68); SVG vectors preserved; duplicate assets embedded once.
- Interactive Vue components that exist only on the website are replaced by a short static note pointing readers to the online version.
Online version
The always-up-to-date site (including appendices and interactive demos) is available at https://datawhalechina.github.io/easy-vibe/. Source: https://github.com/datawhalechina/easy-vibe.
Easy-Vibe 开放教材 v0.4.0
本版本提供 Easy-Vibe 开放教材的 10 种语言离线版本,格式为 PDF 与 EPUB。每本书仅包含 Stage 1、Stage 2、Stage 3 三个正文阶段,不包含附录章节,以便控制下载体积。
内容范围
- 仅包含 Stage 1、Stage 2、Stage 3,不含附录。
- 每本约 55 个章节,覆盖从 AI 产品原型到全栈开发的完整学习路径。
语言
代码 语言 zh-cn简体中文 zh-tw繁體中文 enEnglish ja-jp日本語 ko-kr한국어 es-esEspañol fr-frFrançais de-deDeutsch vi-vnTiếng Việt ar-saالعربية(从右向左排版) 下载
本 Release 附带 20 个文件,命名规则为
easy-vibe-open-textbook-<locale>-v0.4.0.{pdf,epub}。- PDF:A4 排版、矢量字体、可打印、含可跳转目录,单本 39–48 MB。
- EPUB:EPUB3 流式排版,适配手机、电纸书与 Apple Books,单本 58–67 MB。
- 阿拉伯语(
ar-sa)使用 XeLaTeX + polyglossia 进行从右向左排版。
桌面阅读与打印建议使用 PDF;手机与电子墨水屏建议使用 EPUB。
构建说明
- PDF:XeLaTeX 排版,按语言配置字体栈;随后通过 Ghostscript 二次压缩(
/printer、144 dpi 双三次下采样、sRGB、字体子集化、重复图像去重)。 - EPUB:栅格图最长边统一缩至 1200 px,大图 PNG 自动转换为 JPEG(质量 68),SVG 矢量图保留,重复素材仅打包一次。
- 网站上的交互式 Vue 组件在离线版中替换为一条简短的静态说明,指向在线版本。
在线版本
包含附录章节与交互式 Demo 的在线文档:https://datawhalechina.github.io/easy-vibe/ 。源码仓库:https://github.com/datawhalechina/easy-vibe 。
用户点评
登录用户的真实使用记录,可按版本和硬件筛选还没有人点评。第一个说出真实体验的人最有价值。
Table of Contents
- Why Easy-Vibe
- What You Can Build
- News
- Who This Is For
- Your Learning Paths
- Study Suggestions
- How To Learn
- Run Locally
- Other Courses
- Contributing & Contributors
- LICENSE
Why Easy-Vibe
Want an expense tracker? Say it.
Need a booking system with WeChat login? Say it.
Want a blog with comments? Say it.
In the AI era, programming starts by describing what you want.
Easy-Vibe teaches you how to turn that into a real product.
What You Can Build
Illustrative project previews. Explore the corresponding tutorials:
AI Copywriter · Travel Planner · Personal Blog · Browser AI Assistant
🔥 News
- [2026-08-12] 📘 Stage 1 has been restructured and polished: The beginner path now starts with real problems and proceeds through finding opportunities, choosing a direction, understanding user needs, conducting interviews, narrowing the solution, building a prototype, integrating AI, and completing a presentable project. The explanations, real-world examples, images, and hands-on exercises have also been revised. Stage 1 is now better suited to complete beginners, first-time product builders, and indie developers who want to move from a real need to a prototype that can be shown to users. 👉 Start with Stage 1
- [2026-06-17] 🌍 Full multilingual coverage complete: All tutorial content (Stages 1-3) is now available in 10 languages (zh-cn, en, zh-tw, ja-jp, ko-kr, es-es, fr-fr, de-de, ar-sa, vi-vn), covering product prototyping, full-stack development, and cross-platform development.
- [2026-03-29] ✨ Vibe Stories launched and upgraded with real user journeys: Added a new homepage Vibe Stories section with an interactive carousel and dedicated story pages, then replaced placeholder content with four real user stories featuring a rural primary school teacher, a college student, a high school IT teacher, and a truck driver who built real products with AI. 👉 View the stories
- [2026-03-26] 🚀 Major Stage 2 practice update: Completed the SaaS capstone project "Your First SaaS Full-Stack App: Copywriting Generator Website" and substantially expanded the "How to integrate Stripe and payment systems" section, plus key content around multi-product UI and WeChat Mini Program backend workflows.
- [2026-03-25] 📚 New appendix: User Research and Requirement Validation: Added four new articles covering idea sourcing, the Double Diamond model, Jobs to Be Done, and The Mom Test to help beginners discover and validate product ideas. 👉 Read the appendix
- [2026-03-25] 📚 English documentation fully updated: Stage 2 (Full-stack Development) and Stage 3 (Advanced Development) are now fully available in English. 👉 Start learning
- [2026-03-02] 🦞 OpenClaw and AI Agent friendly support: Added
llms.txtso OpenClaw, Claude, Cursor, Trae, and other AI agents can quickly understand the repository structure and find the right tutorial content. - [2026-03-01] The Advanced Development section has been comprehensively upgraded with deep guides for Claude Code, including MCP, Skills, Agent Teams, and more, along with eight cross-platform project tutorials.
- [2026-02-25] Updated the Appendix Knowledge Base, now covering 9 knowledge areas and 80+ interactive topics.
- [2026-01-27] Added Android and iOS app development tutorials.
- [2026-01-19] Released interactive demos for Prompt Engineering, AI history, authentication design, Git principles, and more.
- [2026-01-16] Reorganized the project structure and formally established a beginner entry path.
- [2026-01-14] Completed a large update to the Stage 1 product prototyping docs.
- [2026-01-13] Refactored the documentation architecture and fully enabled multi-language support.
- [2026-01-01] Released the core learning map for the project.
Who This Is For
- Complete beginners: Build your first project first, then understand how it works
- Product managers / founders: Validate ideas fast and build MVPs at low cost
- Students: Develop practical skills for the AI era
- Junior developers: Learn the full path from idea to launch
- Mid-level and senior developers: Upgrade your AI collaboration workflow for complex projects
Your Learning Paths
🎮 I want a fast first win
Best for: Everyone What you will learn: What AI coding actually feels like through a simple, concrete hands-on example What you will get: A clear first impression of vibe coding and how to work with AI by conversation
💡 I want to turn an idea into a product prototype
Best for: Beginners / product managers / founders What you will learn: Learning roadmap, AI IDE tools, idea validation, prototyping, AI capability integration, and full demo iteration What you will get: A demoable AI product prototype you can actually show to users or teammates
🚀 I want to build full-stack products end to end
Best for: Junior developers / indie hackers / advanced learners What you will learn: Frontend workflows, design-to-code, databases, backend APIs, deployment, billing, and major projects What you will get: The ability to independently ship modern AI-enabled web applications
AI-Native: I want advanced Claude Code and agent workflows
Best for: Developers interested in AI-native engineering What you will learn: Claude Code, MCP, Skills, Agent Teams, long-running tasks, Spec Coding, and cross-platform app delivery What you will get: A stronger workflow for complex AI-assisted development and automation
📚 I want reference material and fundamentals
Best for: Everyone What you will learn: Computer fundamentals, frontend/backend basics, infrastructure, AI principles, and engineering practices What you will get: A long-term reference knowledge base covering 9 major knowledge areas
Study Suggestions
- If you are a beginner, product manager, or founder, start with Stage 1
- If you want to move from prototypes to full-stack delivery, start with Stage 2
- If you want advanced Claude Code workflows or cross-platform projects, go to Stage 3
- If you get blocked by concepts or missing background knowledge, use the Appendix Knowledge Base
📖 Content Navigation
I. Beginner Entry
| Section | Key Content |
|---|---|
| Learning Map | A guided overview of the full learning journey |
| AI Era: If You Can Speak, You Can Code | Get your first feel for AI coding through examples like Snake |
| Master AI Programming Tools | Learn how AI IDE tools work and build simple local projects with them |
| Find Great Ideas | Learn how to discover and validate product ideas worth building |
| Build Product Prototypes | Move from requirements to single-page and multi-page product prototypes |
| Integrate AI Capabilities | Integrate text, image, and video AI features |
| Complete project practice | Simulate real scenarios, collect user feedback, and iterate on a full project |
Appendix: Product and Business Thinking
| Section | Key Content |
|---|---|
| Product Thinking and Solution Design | Core frameworks for going from zero to one with a product |
| AI Application Scenario Reference (B2B & B2C) | B2B industry and B2C consumer AI application scenarios |
Appendix: User Research and Requirement Validation
| Section | Key Content |
|---|---|
| Where to find ideas: 3 reference sources that work best for beginners | Build a reliable pipeline for finding concrete product opportunities |
| Double Diamond: first do the right thing, then do it right | Use a structured process to move from scattered inspiration to a workable direction |
| Use Jobs to Be Done to find what users really want done | Analyze user goals through real tasks instead of surface-level feature requests |
| The Mom Test: a user interview method for validating demand | Learn how to ask better questions and avoid false-positive feedback |
Appendix: Technical Solutions
| Section | Key Content |
|---|---|
| What to do if you encounter errors | Common vibe coding issues and how to troubleshoot them |
| Comparison of Seven AI Programming Tools | Compare major AI coding platforms through hands-on testing |
| Design Websites with Agents | Learn multi-agent collaboration in practice |
More Beginner Practice
- Clone from a Screenshot: Your First Imitation Exercise
- Publish Your Vibe Coding Project on ModelScope
II. Junior and Mid-Level Developers
Frontend
| Section | Key Content |
|---|---|
| Frontend 0: Build Your Own Asset-Production Agent with Lovart | Use Nanobanana and Lovart to batch-generate visual assets and build a drawing agent with intent recognition |
| Frontend 1: Figma & MasterGo Basics | Learn the workflow from design drafts to implementation-ready UI thinking |
| Frontend 2: Build Your First Modern App - UI Design | Learn the UI design foundations behind modern application interfaces |
| Frontend 3: UI Guidelines and Multi-Product Design | Improve consistency and aesthetics across multiple products with shared UI rules |
| Frontend 4: Make Interfaces Beautiful with LLMs and Skills | Use prompts and plugins to make AI generate more polished, distinctive interfaces |
| Frontend 4: Let's Build Hogwarts Portraits | Build an interactive AI-image frontend project from scratch |
| Frontend 6: From Design Prototype to Project Code | Turn design prototypes into frontend code that can really run in the browser |
| Frontend 7: Upgrade Your UI with Modern Component Libraries | Use component libraries to build professional interfaces faster |
Backend
| Section | Key Content |
|---|---|
| Backend 1: Learn Git and GitHub | Master core version control operations and collaboration workflows with Git |
| Backend 2: From Database to Supabase | Learn relational database basics and use Supabase as a modern BaaS platform |
| Backend 3: Backend API Design and Development | Use AI to assist API design, backend code generation, and API documentation |
| Backend 4: Ship Your Product Prototype | Quickly deploy full-stack applications to the cloud with Zeabur |
| Backend 5: From IDEs to CLI AI Coding Tools | Explore terminal-first AI coding workflows for modern development |
| Backend 6: Integrate Stripe and Other Billing Systems | Add monetization with payment and billing capabilities |
Major Projects
| Section | Key Content |
|---|---|
| Major Project 1: Your First SaaS Full-Stack App - AI Copywriting Website | Build an AI marketing copy workspace with login, generation, billing, and admin management |
| Major Project 2: Online Exam and Management System | Build an online exam system with question generation, test-taking flows, and admin tools |
More Project Practice
AI Capabilities Appendix
| Section | Key Content |
|---|---|
| AI 1: Dify Basics & Knowledge Base Integration | Learn to build AI applications with Dify and integrate private knowledge bases |
More Full-Stack Tutorials
III. Advanced Developers
Claude Code Core Skills
| Section | Key Content |
|---|---|
| Getting started with Claude Code | Installation, setup, fundamentals, and useful commands |
| Claude Code MCP guide | Connect Claude Code to GitHub, databases, APIs, and other services through MCP |
| Claude Code Skills guide | Package expertise into reusable skills you can use again and again |
| How to keep Claude Code working for long-running tasks | Design long-running tasks so coding tools can keep working until the job is done |
| Claude Agent Teams guide | Coordinate multiple AI instances like a real development team |
| Claude Code Superpowers for engineering-grade development | Help AI produce engineering-grade code with TDD and best practices |
| Claude Code workflow best practices | Best practices for refactoring, code review, and daily development |
| Building Software End to End with GitHub Issues: From Product Conversation to a macOS App | Spec → Issues → implementation → tests and review |
| Claude Code remote development on mobile | Use Claude Code beyond the desktop and build a productive remote workflow on mobile devices |
| Claude Agent SDK complete guide | Build custom agent workflows and integrate Claude into your own tools with the SDK |
| From vibe coding to spec coding | Move from ad-hoc prompting to a more structured, specification-driven AI development workflow |
Cross-Platform Development
| Section | Key Content |
|---|---|
| How to choose the right platform for your app | Compare app forms and choose the right platform based on users, scenarios, and delivery goals |
| Build a WeChat Mini Program | Understand the ecosystem and ship a frontend mini program from template to launch |
| Build a WeChat Mini Program with backend | Add backend logic and databases to complete the full business loop |
| Build an Android app | Learn Android app development with a modern native workflow |
| Build an iOS app | Learn iOS app development and the conventions of the Apple ecosystem |
| Build a local PWA app | Turn a website into a real app with offline support, push, and installation |
| Build a browser AI assistant extension | Create a Chrome extension that summarizes any page with either cloud APIs or built-in AI |
| Build an Electron desktop app | Build a voice-to-text desktop app with Electron for three platforms |
| Rapidly build and mint an NFT | Write a smart contract from scratch, deploy it, and mint your own NFT |
| Build a VS Code extension | Build an AI project assistant with templates, code chat, and multi-file Q&A |
| Build an industrial-grade Qt desktop app | Create a real-time Qt HMI system with trends, alerts, and monitoring |
AI Capabilities Appendix
| Section | Key Content |
|---|---|
| What is RAG and how does it work | Build a systematic understanding of RAG principles and common architectures |
| Intermediate and advanced RAG workflows with LangGraph | Design multi-step workflows and more advanced RAG systems |
More Advanced Tutorials
- From a Web Page to Real Software, and Then to an AI-Native Product
- Build a Store Inspection App with React Native and Expo
- How to Build a Cross-Platform App with Flutter
- How to Build Platform, Pixel-Art, and 3D Games with Godot
- How to Publish the Application You Built
📚 Appendix Knowledge Base
Covering 9 major knowledge areas and 80+ interactive topics, this appendix uses animation and visual components to help you intuitively understand core concepts from computer fundamentals to the AI frontier.
🎓 Other Courses
🛠️ How To Learn
- Read and practice the sections that match your current level. If you get stuck, feel free to open an issue.
💻 Run Locally
Modern approach
In an AI IDE chat window such as VS Code, Cursor, or Trae, you can simply say:
Please help me run this project locally.
Traditional approach
npm installnpm run dev- Open
http://localhost:3000in your browser.
Other Courses
Our team has also created other courses! Check them out:
Hands-on Modern RL: An open-source, hands-on curriculum bridging the gap from basic RL concepts to LLM alignment, RLVR, and advanced Agentic systems.
Learn Harness Engineering: A comprehensive guide to harness engineering.
🤝 Contributing & Contributors
- If you find an issue or see something that can be improved, feel free to open an issue. If nobody replies, you can also contact the Datawhale support team.
- If you want to contribute, open a pull request. If nobody replies, you can also contact the Datawhale support team.
- If you want to start a new Datawhale open-source project, please follow the Datawhale Open Source Project Guide.
🙏 Contributors
- Sanbu - Project Lead (Datawhale member)
- Fang Ke - Mentor (Datawhale member, Tsinghua University)
- Yerim Kang (Practice projects, Tsinghua University)
- Zhilin Zhao (Practice projects, Tsinghua University)
- Yixuan Li (Visual design, Tsinghua University)
- Siyi Liu (Practice projects, Tsinghua University)
- Lixin Liu (Practice projects, Tsinghua University)
- Everyone in the AI Vibe Coding 101 internal testing group who shared suggestions and feedback
Special Thanks
- Thanks to OpenAI for providing compute support for the development of this project
- Thanks to @Sm1les for the help and support on this project
- Thanks to every contributor and everyone who supported the project with feedback and stars ❤️