{"data":{"slug":"fancyboi999-ai-engineering-from-scratch-zh","name":"ai-engineering-from-scratch-zh","tagline":"AI Engineer Learning Path · Chinese Translation","github_url":"https://github.com/fancyboi999/ai-engineering-from-scratch-zh","owner":"fancyboi999","repo":"ai-engineering-from-scratch-zh","owner_avatar_url":"https://avatars.githubusercontent.com/u/135568692?v=4","primary_language":"Python","stars":1091,"forks":180,"topics":["agents","ai","ai-agents","ai-engineering","chinese","chinese-translation","computer-vision","course","deep-learning","from-scratch","generative-ai","learn-ai","llm","machine-learning","mcp","nlp","python","reinforcement-learning","transformers","tutorial"],"archived":false,"github_pushed_at":"2026-09-21T07:11:13+00:00","maintenance_label":"Very active","stars_delta_30d":190,"url":"https://www.graphcanon.com/tools/fancyboi999-ai-engineering-from-scratch-zh","markdown_url":"https://www.graphcanon.com/tools/fancyboi999-ai-engineering-from-scratch-zh.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/fancyboi999-ai-engineering-from-scratch-zh","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=fancyboi999-ai-engineering-from-scratch-zh","description":"Agent工程师最全学习路径 · 从零精通 AI 工程 · 20 阶段 503 课 · 中文全量翻译 + 配套站点 + 动画讲解视频 · 如何成为 AI Agent 工程师的修成指南","homepage_url":"https://aieng-zh.cn","license":"MIT","open_issues":1,"watchers":10,"ai_summary":"A comprehensive learning path with 503 lessons and 20 phases to become proficient in AI engineering. Includes Python code, translation into simplified Chinese, an accompanying website, and animated tutorial videos.","readme_excerpt":"
\n\n```text\n░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒\n```\n\n> 通过推导、代码和实验学习 AI 工程。\n>\n> 523 节课，20 个阶段，覆盖 Python、TypeScript、Rust、Julia。课程配有中文正文、测验、\n> 可运行示例和可复用产物。免费阅读，开源，采用 MIT 许可。\n>\n> 从基础算法到 LLM 应用、agent 与生产系统，按你的目标选择学习路径。\n\n> 本项目是 [AI Engineering from Scratch](https://github.com/rohitg00/ai-engineering-from-scratch)（作者 [Rohit Ghumare](https://github.com/rohitg00)，MIT 协议）的**简体中文衍生版**。衷心感谢原作者创作并开源了这套课程。\n\n### 这个中文版做了什么\n\n中文版提供课程翻译、配套视频、交互式学习网站和 AI 导师：\n\n| | |\n|---|---|\n| 🇨🇳 **全站简体中文** | 523 节课正文、243 条术语表、测验题、`mermaid` 流程图、交互图表标签全部中文化（`agent`、`token`、`transformer` 等技术术语按惯例保留英文） |\n| 🌐 **独立中文网站 [aieng-zh.cn](https://aieng-zh.cn)** | 可搜索的课程目录、[AI 工程学习路径](https://aieng-zh.cn/learning-paths.html)、学习进度追踪、可拖动的交互式图表、命令面板（`Cmd / Ctrl + K`）、深色模式 |\n| 🎬 **配套动画讲解视频** | 333 节中文配音动画已上线，覆盖阶段 0–14 的全部课程。可在课程页内嵌播放，提供直链与 B 站播放源，配合正文、数学推导和代码实践学习 |\n| 🔍 **为 AI 检索优化** | 构建时自动生成 `sitemap.xml` / `llms.txt` / 结构化数据，方便被搜索引擎和 AI 助手引用 |\n| ✅ **课数一致性护栏** | CI 自动校验课程数（`node site/build.js --check`），防止课程列表与磁盘上的实际内容漂移 |\n\n> 翻译怎么翻见 [TRANSLATION.md](TRANSLATION.md)。课程结构、代码与上游保持一致，译文持续跟进上游更新。\n\n**目录** · [从这里开始](#从这里开始选择你想构建的内容) · [AI 导师](#30-秒添加-ai-导师) · [怎么运作](#怎么运作) · [课程结构](#课程的结构) · [学习路径](https://aieng-zh.cn/learning-paths.html) · [一节课的样子](#一节课的样子) · [快速开始](#快速开始) · [每节课都有产出](#每节课都有产出) · [课程目录](#contents) · [工具箱](#工具箱) · [参与贡献](#参与贡献)\n\n## 从这里开始：选择你想构建的内容\n\n开始前不需要先扫完 523 节课。选一个目标即可。每个链接都对应 GitHub 或网站上的同一套课程，两处使用相同的课程代码。\n\n| 你的目标 | 在 GitHub 上学习 | 在网站上学习 |\n|---|---|---|\n| 我是新手，想要完整地打牢基础 | [阶段 0 · 配置与工具链](phases/00-setup-and-tooling/) | [开发环境](https://aieng-zh.cn/lessons/00-setup-and-tooling/01-dev-environment/) |\n| 我懂 Python，想学数学与机器学习基础 | [阶段 1 · 数学基础](phases/01-math-foundations/) | [线性代数直觉](https://aieng-zh.cn/lessons/01-math-foundations/01-linear-algebra-intuition/) |\n| 我想构建生产级 LLM 应用 | [阶段 11 · LLM 工程](phases/11-llm-engineering/) | [提示词工程](https://aieng-zh.cn/lessons/11-llm-engineering/01-prompt-engineering/) |\n| 我想构建自主 agent | [阶段 14 · Agent 工程](phases/14-agent-engineering/) | [Agent 循环](https://aieng-zh.cn/lessons/14-agent-engineering/01-the-agent-loop/) |\n| 我想在真实代码仓库中使用 coding agent | [Agent 辅助工程路径](learning-paths/using-coding-agents.json) | [Agent 辅助工程](https://aieng-zh.cn/lessons/14-agent-engineering/31-agent-workbench-why-models-fail/?learningPath=using-coding-agents) |\n| 我想在编码实施前把产品方案想透定准 | [产品判断与交付路径](learning-paths/shaping-the-build.json) | [产品判断与交付](https://aieng-zh.cn/lessons/14-agent-engineering/47-outcomes-before-output/?learningPath=shaping-the-build) |\n| 我想基于模型上下文协议（MCP）构建系统 | [模型上下文协议（MCP）路线](phases/13-tools-and-protocols/README.md#model-context-protocol-mcp-path) | [模型上下文协议（MCP）路径](https://aieng-zh.cn/lessons/13-tools-and-protocols/06-mcp-fundamentals/?learningPath=model-context-protocol) |\n| 我想编写并交付 Agent Skills | [Agent Skills 快速路线](phases/13-tools-and-protocols/READM","github_created_at":"2026-05-26T12:45:07+00:00","created_at":"2026-07-11T12:27:36.722033+00:00","updated_at":"2026-09-23T06:00:21.429712+00:00","categories":[{"slug":"ai-agents","name":"AI Agents","url":"https://www.graphcanon.com/categories/ai-agents","markdown_url":"https://www.graphcanon.com/categories/ai-agents.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/ai-agents"},{"slug":"developer-tools","name":"Developer Tools","url":"https://www.graphcanon.com/categories/developer-tools","markdown_url":"https://www.graphcanon.com/categories/developer-tools.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/developer-tools"},{"slug":"inference-serving","name":"Inference & Serving","url":"https://www.graphcanon.com/categories/inference-serving","markdown_url":"https://www.graphcanon.com/categories/inference-serving.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/inference-serving"},{"slug":"llm-frameworks","name":"LLM Frameworks","url":"https://www.graphcanon.com/categories/llm-frameworks","markdown_url":"https://www.graphcanon.com/categories/llm-frameworks.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/llm-frameworks"},{"slug":"model-training","name":"Model Training","url":"https://www.graphcanon.com/categories/model-training","markdown_url":"https://www.graphcanon.com/categories/model-training.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/model-training"}],"tags":[{"slug":"agents","name":"agents"},{"slug":"ai-engineering","name":"ai-engineering"},{"slug":"chinese-translation","name":"chinese-translation"},{"slug":"computer-vision","name":"computer-vision"},{"slug":"course-materials","name":"course-materials"},{"slug":"deep-learning","name":"deep-learning"},{"slug":"tutorial","name":"tutorial"}],"trust":{"provenance":{"is_fork":false,"github_id":1250240320,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-23T06:00:20.661Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":0,"days_since_push":1,"last_release_at":null,"stars_delta_30d":190,"open_issues_delta_30d":0},"security_summary":{"status":"findings","scanner":"osv@v1","low_count":83,"high_count":0,"last_scan_at":"2026-07-11T12:27:39.061Z","medium_count":0,"scan_profile":"deps","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-23T06:00:21.110Z"},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-09-23T06:00:21.110Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-09-23T06:00:21.110Z"}},"decision_facts":{"hosting":null,"pricing":{"model":"freemium","summary":"Free and open-source under the MIT License with no cost for usage or source access. Contributions are encouraged but not required."},"requirements":{"min_ram_gb":4,"requires_docker":false},"constraints":{"min_ram_gb":4,"pricing_model":"freemium","requires_docker":false},"when_to_use":["Use when you need detailed and structured learning materials in simplified Chinese to master AI engineering concepts and practical implementations.","Suitable if your primary language or preferred educational medium is simplified Chinese, given the thorough translation and adaptation."],"when_not_to_use":["Avoid using this resource if you are primarily interested in languages other than Python, TypeScript, Rust, and Julia as the course content may not cover alternative ecosystems extensively.","Do not use this curriculum if instant accessibility to completed solutions is preferred; it focuses on self-driven coding exercises and less passive learning methods."],"source":"enrich:decision_facts","observed_at":"2026-07-17T00:07:47.362Z"},"constraint_facets":{"min_ram_gb":4,"pricing_model":"freemium","requires_docker":false},"decision_summary":[{"label":"Pricing","value":"freemium - Free and open-source under the MIT License with no cost for usage or source access. Contributions are encouraged but not required."},{"label":"Requirements","value":"Min 4 GB RAM"},{"label":"Adopt for","value":"A comprehensive Chinese-translated curriculum with 503 lessons across 20 phases for AI engineering mastery."},{"label":"License detail","value":"The MIT License allows free usage and modification under specific terms, promoting open-source collaboration."}]}}
![\"AI](\"assets/banner.svg\")
\n![\"在线阅读](\"https://img.shields.io/badge/在线阅读-aieng--zh.cn-3553ff?style=flat-square&labelColor=fafaf5\"){kind=icon}
![\"523](\"https://img.shields.io/badge/lessons-523-3553ff?style=flat-square&labelColor=fafaf5\"){kind=icon}
![\"20](\"https://img.shields.io/badge/phases-20-3553ff?style=flat-square&labelColor=fafaf5\"){kind=icon}
![\"MIT](\"https://img.shields.io/badge/license-MIT-1a1a1a?style=flat-square&labelColor=fafaf5\"){kind=icon}
![\"GitHub](\"https://img.shields.io/github/stars/fancyboi999/ai-engineering-from-scratch-zh?style=flat-square&labelColor=fafaf5&color=3553ff&cacheSeconds=21600\")