diff --git a/README.md b/README.md index 4193007..f7a29f6 100644 --- a/README.md +++ b/README.md @@ -1,58 +1,52 @@ + +> [!NOTE] +> 本文档由 WeHub 基于上游 README 翻译整理，属于社区翻译，非官方中文文档。 +> [English](./README.en.md) · [原始项目](https://github.com/rohitg00/ai-engineering-from-scratch) · [上游 README](https://github.com/rohitg00/ai-engineering-from-scratch/blob/HEAD/README.md) +> 原作者、版权与许可证归属以原始项目及本仓库 LICENSE 文件为准。 +

- AI Engineering from Scratch — reference manual banner + AI Engineering from Scratch — 参考手册横幅

MIT License - 503 lessons - 20 phases + 503 节课 + 20 个阶段 GitHub stars - Website + 网站

-## From the creator of [Agent Memory - #1 Persistent memory ⭐](https://github.com/rohitg00/agentmemory) GitHub stars which naturally works with any agents or chat assistants. +## 来自 [Agent Memory - #1 持久化记忆（Persistent memory）⭐](https://github.com/rohitg00/agentmemory) GitHub stars 的创作者，可与任何 agent 或聊天助手自然配合使用。 ``` ░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒ ``` -> **84% of students already use AI tools. Only 18% feel prepared to use them -> professionally.** This curriculum closes that gap. +> **84% 的学生已在用 AI 工具，却只有 18% 觉得自己能专业地使用它们。** 本课程体系旨在弥合这一差距。 > -> 503 lessons. 20 phases. ~320 hours. Python, TypeScript, Rust, Julia. Every lesson ships -> a reusable artifact: a prompt, a skill, an agent, an MCP server. Free, open source, MIT. +> 503 节课、20 个阶段、约 320 小时。Python、TypeScript、Rust、Julia。每节课都会交付一个可复用产物：prompt、skill、agent 或 MCP server。免费、开源、MIT 许可。 > -> You don't just learn AI. You build it. End-to-end. By hand. +> 你不只是学 AI，而是亲手把它做出来。端到端、从零开始。 -

150,639 readers  ·  241,669 page views in the last 30 days  ·  as of 2026-06-07

+

150,639 位读者  ·  过去 30 天 241,669 次页面浏览  ·  截至 2026-06-07

-## How this works +## 运作方式 -Most AI material teaches in scattered pieces. A paper here, a fine-tuning post there, a -flashy agent demo somewhere else. The pieces rarely line up. You ship a chatbot but can't -explain its loss curve. You hook a function to an agent but can't say what attention does -inside the model that's calling it. +大多数 AI 资料都是零散教学的：这里一篇论文、那里一篇微调博文、别处一个炫目的 agent 演示。这些碎片很少能拼成一条线。你能上线一个聊天机器人，却说不清它的 loss curve（损失曲线）。你能给 agent 挂一个函数，却说不清调用它的模型内部 attention（注意力）在做什么。 -This curriculum is the spine. 20 phases, 503 lessons, four languages: Python, TypeScript, -Rust, Julia. Linear algebra at one end, autonomous swarms at the other. Every algorithm -gets built from raw math first. Backprop. Tokenizer. Attention. Agent loop. By the time -PyTorch shows up, you already know what it's doing under the hood. +本课程体系就是那条主线。20 个阶段、503 节课、四种语言：Python、TypeScript、Rust、Julia。一端是线性代数，另一端是自主 swarm（群体智能）。每个算法都先从原始数学推导并亲手实现。反向传播（Backprop）。Tokenizer。Attention。Agent loop。等到 PyTorch 登场时，你已经知道它在底层做了什么。 -Each lesson runs the same loop: read the problem, derive the math, write the code, run -the test, keep the artifact. No five-minute videos, no copy-paste deploys, no hand-holding. -Free, open source, and built to run on your own laptop. +每节课都遵循同一循环：读题、推导数学、写代码、跑测试、保留产物。没有五分钟视频，没有复制粘贴式部署，也没有手把手哄着你。免费、开源，并且设计为在你自己的笔记本电脑上运行。 ``` ░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒ ``` -## The shape of the curriculum +## 课程结构 -Twenty phases stack on top of each other. Math is the floor. Agents and production are the roof. -Skip ahead if you already know the lower layers, but don't skip and then wonder why something at -the top is breaking. +二十个阶段层层叠放。数学是地基，agent 与生产部署是屋顶。若你已掌握底层内容，可以跳过；但若跳过后又在高层遇到问题，就别奇怪为什么会崩。 ```mermaid %%{init: {'theme':'base','themeVariables':{'primaryColor':'#fafaf5','primaryTextColor':'#1a1a1a','primaryBorderColor':'#3553ff','lineColor':'#3553ff','fontFamily':'JetBrains Mono','fontSize':'12px'}}}%% @@ -84,9 +78,9 @@ flowchart TB ░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒ ``` -## The shape of a lesson +## 单节课的结构 -Each lesson lives in its own folder, with the same structure across the entire curriculum: +每节课都在独立文件夹中，整个课程体系采用统一结构： ``` phases/-/-/ @@ -96,9 +90,7 @@ phases/-/-/ └── outputs/ prompts, skills, agents, or MCP servers this lesson produces ``` -Every lesson follows six beats. The *Build It / Use It* split is the spine — you implement the -algorithm from scratch first, then run the same thing through the production library. You -understand what the framework is doing because you wrote the smaller version yourself. +每节课遵循六个节拍。*Build It / Use It*（先实现、再使用）是主线——你先从零实现算法，再用生产级库跑同一套东西。因为你亲手写过简化版，所以你能理解框架在做什么。 ```mermaid %%{init: {'theme':'base','themeVariables':{'primaryColor':'#fafaf5','primaryTextColor':'#1a1a1a','primaryBorderColor':'#3553ff','lineColor':'#3553ff','fontFamily':'JetBrains Mono','fontSize':'13px'}}}%% @@ -110,15 +102,13 @@ flowchart LR U --> S["SHIP IT
prompt · skill · agent · MCP"] ``` -## Getting started +## 入门方式 -Three ways in. Pick one. +三种入口，任选其一。 -**Option A — read.** Open any completed lesson on -[aiengineeringfromscratch.com](https://aiengineeringfromscratch.com) or expand a phase under -[Contents](#contents). No setup, no cloning. +**选项 A — 阅读。** 在 [aiengineeringfromscratch.com](https://aiengineeringfromscratch.com) 打开任意已完成的课时，或在 [目录](#contents) 下展开某个阶段。无需配置，无需克隆。 -**Option B — clone and run.** +**选项 B — 克隆并运行。** ```bash git clone https://github.com/rohitg00/ai-engineering-from-scratch.git @@ -126,14 +116,13 @@ cd ai-engineering-from-scratch python phases/01-math-foundations/01-linear-algebra-intuition/code/vectors.py ``` -**Option C — find your level *(recommended)*.** Skip ahead intelligently. Inside Claude, Cursor, Codex, OpenClaw, Hermes, or any agent with the curriculum skills installed: +**选项 C — 找准你的水平（*推荐*）。** 智能跳过已掌握内容。在 Claude、Cursor、Codex、OpenClaw、Hermes，或任何已安装本课程 skills 的 agent 中： ```bash /find-your-level ``` -Ten questions. Maps your knowledge to a starting phase, builds a personalized path with hour -estimates. After each phase: +十个问题。将你的知识映射到起始阶段，并生成带学时估算的个性化路径。每个阶段结束后： ```bash /check-understanding 3 # quiz yourself on phase 3 @@ -142,26 +131,25 @@ ls phases/03-deep-learning-core/05-loss-functions/outputs/ # └── prompt-loss-debugger.md ``` -### Prerequisites +### 前置要求 -- You can write code (any language; Python helps). -- You want to understand how AI **actually works**, not just call APIs. +- 你会写代码（任意语言；会 Python 更好）。 +- 你想理解 AI **究竟如何工作**，而不只是调用 API。 -### Built-in agent skills (Claude, Cursor, Codex, OpenClaw, Hermes) +### 内置 agent skills（Claude、Cursor、Codex、OpenClaw、Hermes） -| Skill | What it does | +| Skill | 作用 | |---|---| -| [`/find-your-level`](.claude/skills/find-your-level/SKILL.md) | Ten-question placement quiz. Maps your knowledge to a starting phase and produces a personalized path with hour estimates. | -| [`/check-understanding `](.claude/skills/check-understanding/SKILL.md) | Per-phase quiz, eight questions, with feedback and specific lessons to review. | +| [`/find-your-level`](.claude/skills/find-your-level/SKILL.md) | 十题定级测验。将你的知识映射到起始阶段，并生成带学时估算的个性化路径。 | +| [`/check-understanding `](.claude/skills/check-understanding/SKILL.md) | 按阶段测验，八道题，附反馈及需复习的具体课时。 | ``` ░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒ ``` -## Every lesson ships something +## 每节课都有可交付物 -Other curricula end with *"congratulations, you learned X."* Each lesson here ends with a -**reusable tool** you can install or paste into your daily workflow. +其他课程常以*“恭喜，你学会了 X”*收尾。这里的每节课都以一个**可复用工具**结束——你可以安装它，或粘贴到日常工作中。 @@ -171,26 +159,25 @@ Other curricula end with *"congratulations, you learned X."* Each lesson here en - - - - + + + +
FIG_001.D MCP servers
FIG_001 · D
MCP SERVERS
Paste into any AI assistant for expert-level help on a narrow task.Drop into Claude, Cursor, Codex, OpenClaw, Hermes, or any agent that reads SKILL.md.Deploy as autonomous workers — you wrote the loop yourself in Phase 14.Plug into any MCP-compatible client. Built end-to-end in Phase 13.粘贴到任意 AI 助手，获取针对窄任务的专家级帮助。放入 Claude、Cursor、Codex、OpenClaw、Hermes，或任何会读取 SKILL.md 的 agent。部署为自主 worker——你在第 14 阶段亲手写过循环。接入任意兼容 MCP 的客户端。在第 13 阶段端到端构建。
-> Install the lot with `python3 scripts/install_skills.py`. Real tools, not homework. -> By the end of the curriculum, you have a portfolio of 503 artifacts you actually -> understand because you built them. +> 使用 `python3 scripts/install_skills.py` 一次性安装全部内容。真实工具，而非作业练习。 +> 课程结束时，你将拥有一份包含 503 个产出物的作品集，而且你真正理解它们——因为都是你亲手构建的。 -### FIG_002 · A worked sample +### FIG_002 · 完整示例 -Phase 14, lesson 1: the agent loop. ~120 lines of pure Python, no dependencies. +第 14 阶段，第 1 课：智能体循环（agent loop）。约 120 行纯 Python，无依赖。
-**`code/agent_loop.py`**   build it +**`code/agent_loop.py`**   动手构建 ```python def run(query, tools): @@ -209,7 +196,7 @@ def run(query, tools): -**`outputs/skill-agent-loop.md`**   ship it +**`outputs/skill-agent-loop.md`**   上线交付 ```markdown --- @@ -240,15 +227,15 @@ the agent went wrong and explain why... -## Contents +## 目录 -Twenty phases. Click any phase to expand its lesson list. +共二十个阶段。点击任意阶段可展开其课程列表。 -### Phase 0: Setup & Tooling `12 lessons` -> Get your environment ready for everything that follows. +### Phase 0：环境搭建与工具链 `12 lessons` +> 为后续所有内容准备好你的开发环境。 -| # | Lesson | Type | Lang | +| # | 课程 | 类型 | 语言 | |:---:|--------|:----:|------| | 01 | [Dev Environment](phases/00-setup-and-tooling/01-dev-environment/) | Build | Python | | 02 | [Git & Collaboration](phases/00-setup-and-tooling/02-git-and-collaboration/) | Learn | — | @@ -264,10 +251,10 @@ Twenty phases. Click any phase to expand its lesson list. | 12 | [Debugging & Profiling](phases/00-setup-and-tooling/12-debugging-and-profiling/) | Build | Python |
-Phase 1 — Math Foundations  22 lessons  The intuition behind every AI algorithm, through code. +Phase 1 — 数学基础  22 lessons  通过代码理解每种 AI 算法背后的直觉。
-| # | Lesson | Type | Lang | +| # | 课程 | 类型 | 语言 | |:---:|--------|:----:|------| | 01 | [Linear Algebra Intuition](phases/01-math-foundations/01-linear-algebra-intuition/) | Learn | Python, Julia | | 02 | [Vectors, Matrices & Operations](phases/01-math-foundations/02-vectors-matrices-operations/) | Build | Python, Julia | @@ -295,10 +282,10 @@ Twenty phases. Click any phase to expand its lesson list.
-Phase 2 — ML Fundamentals  18 lessons  Classical ML — still the backbone of most production AI. +Phase 2 — 机器学习基础  18 lessons  经典机器学习——仍是大多数生产级 AI 的支柱。
-| # | Lesson | Type | Lang | +| # | 课程 | 类型 | 语言 | |:---:|--------|:----:|------| | 01 | [What Is Machine Learning](phases/02-ml-fundamentals/01-what-is-machine-learning/) | Learn | Python | | 02 | [Linear Regression from Scratch](phases/02-ml-fundamentals/02-linear-regression/) | Build | Python | @@ -322,10 +309,10 @@ Twenty phases. Click any phase to expand its lesson list.
-Phase 3 — Deep Learning Core  13 lessons  Neural networks from first principles. No frameworks until you build one. +Phase 3 — 深度学习核心  13 lessons  从第一性原理学习神经网络。在你亲手构建框架之前，不使用现成框架。
-| # | Lesson | Type | Lang | +| # | 课程 | 类型 | 语言 | |:---:|--------|:----:|------| | 01 | [The Perceptron: Where It All Started](phases/03-deep-learning-core/01-the-perceptron/) | Build | Python | | 02 | [Multi-Layer Networks & Forward Pass](phases/03-deep-learning-core/02-multi-layer-networks/) | Build | Python | @@ -344,591 +331,591 @@ Twenty phases. Click any phase to expand its lesson list.
-Phase 4 — Computer Vision  28 lessons  From pixels to understanding — image, video, 3D, VLMs, and world models. +阶段 4 — 计算机视觉（Computer Vision）  28 lessons  从像素到理解——图像、视频、3D、视觉语言模型（VLM）与世界模型。
-| # | Lesson | Type | Lang | +| # | 课程 | 类型 | 语言 | |:---:|--------|:----:|------| -| 01 | [Image Fundamentals: Pixels, Channels, Color Spaces](phases/04-computer-vision/01-image-fundamentals/) | Learn | Python | -| 02 | [Convolutions from Scratch](phases/04-computer-vision/02-convolutions-from-scratch/) | Build | Python | -| 03 | [CNNs: LeNet to ResNet](phases/04-computer-vision/03-cnns-lenet-to-resnet/) | Build | Python | -| 04 | [Image Classification](phases/04-computer-vision/04-image-classification/) | Build | Python | -| 05 | [Transfer Learning & Fine-Tuning](phases/04-computer-vision/05-transfer-learning/) | Build | Python | -| 06 | [Object Detection — YOLO from Scratch](phases/04-computer-vision/06-object-detection-yolo/) | Build | Python | -| 07 | [Semantic Segmentation — U-Net](phases/04-computer-vision/07-semantic-segmentation-unet/) | Build | Python | -| 08 | [Instance Segmentation — Mask R-CNN](phases/04-computer-vision/08-instance-segmentation-mask-rcnn/) | Build | Python | -| 09 | [Image Generation — GANs](phases/04-computer-vision/09-image-generation-gans/) | Build | Python | -| 10 | [Image Generation — Diffusion Models](phases/04-computer-vision/10-image-generation-diffusion/) | Build | Python | -| 11 | [Stable Diffusion — Architecture & Fine-Tuning](phases/04-computer-vision/11-stable-diffusion/) | Build | Python | -| 12 | [Video Understanding — Temporal Modeling](phases/04-computer-vision/12-video-understanding/) | Build | Python | -| 13 | [3D Vision: Point Clouds, NeRFs](phases/04-computer-vision/13-3d-vision-nerf/) | Build | Python | -| 14 | [Vision Transformers (ViT)](phases/04-computer-vision/14-vision-transformers/) | Build | Python | -| 15 | [Real-Time Vision: Edge Deployment](phases/04-computer-vision/15-real-time-edge/) | Build | Python | -| 16 | [Build a Complete Vision Pipeline](phases/04-computer-vision/16-vision-pipeline-capstone/) | Build | Python | -| 17 | [Self-Supervised Vision — SimCLR, DINO, MAE](phases/04-computer-vision/17-self-supervised-vision/) | Build | Python | -| 18 | [Open-Vocabulary Vision — CLIP](phases/04-computer-vision/18-open-vocab-clip/) | Build | Python | -| 19 | [OCR & Document Understanding](phases/04-computer-vision/19-ocr-document-understanding/) | Build | Python | -| 20 | [Image Retrieval & Metric Learning](phases/04-computer-vision/20-image-retrieval-metric/) | Build | Python | -| 21 | [Keypoint Detection & Pose Estimation](phases/04-computer-vision/21-keypoint-pose/) | Build | Python | -| 22 | [3D Gaussian Splatting from Scratch](phases/04-computer-vision/22-3d-gaussian-splatting/) | Build | Python | -| 23 | [Diffusion Transformers & Rectified Flow](phases/04-computer-vision/23-diffusion-transformers-rectified-flow/) | Build | Python | -| 24 | [SAM 3 & Open-Vocabulary Segmentation](phases/04-computer-vision/24-sam3-open-vocab-segmentation/) | Build | Python | -| 25 | [Vision-Language Models (ViT-MLP-LLM)](phases/04-computer-vision/25-vision-language-models/) | Build | Python | -| 26 | [Monocular Depth & Geometry Estimation](phases/04-computer-vision/26-monocular-depth/) | Build | Python | -| 27 | [Multi-Object Tracking & Video Memory](phases/04-computer-vision/27-multi-object-tracking/) | Build | Python | -| 28 | [World Models & Video Diffusion](phases/04-computer-vision/28-world-models-video-diffusion/) | Build | Python | +| 01 | [图像基础：像素、通道与色彩空间](phases/04-computer-vision/01-image-fundamentals/) | Learn | Python | +| 02 | [从零实现卷积](phases/04-computer-vision/02-convolutions-from-scratch/) | Build | Python | +| 03 | [CNN：从 LeNet 到 ResNet](phases/04-computer-vision/03-cnns-lenet-to-resnet/) | Build | Python | +| 04 | [图像分类](phases/04-computer-vision/04-image-classification/) | Build | Python | +| 05 | [迁移学习与微调](phases/04-computer-vision/05-transfer-learning/) | Build | Python | +| 06 | [目标检测——从零实现 YOLO](phases/04-computer-vision/06-object-detection-yolo/) | Build | Python | +| 07 | [语义分割——U-Net](phases/04-computer-vision/07-semantic-segmentation-unet/) | Build | Python | +| 08 | [实例分割——Mask R-CNN](phases/04-computer-vision/08-instance-segmentation-mask-rcnn/) | Build | Python | +| 09 | [图像生成——GAN](phases/04-computer-vision/09-image-generation-gans/) | Build | Python | +| 10 | [图像生成——扩散模型](phases/04-computer-vision/10-image-generation-diffusion/) | Build | Python | +| 11 | [Stable Diffusion——架构与微调](phases/04-computer-vision/11-stable-diffusion/) | Build | Python | +| 12 | [视频理解——时序建模](phases/04-computer-vision/12-video-understanding/) | Build | Python | +| 13 | [3D 视觉：点云与 NeRF](phases/04-computer-vision/13-3d-vision-nerf/) | Build | Python | +| 14 | [视觉 Transformer（ViT）](phases/04-computer-vision/14-vision-transformers/) | Build | Python | +| 15 | [实时视觉：边缘部署](phases/04-computer-vision/15-real-time-edge/) | Build | Python | +| 16 | [构建完整视觉流水线](phases/04-computer-vision/16-vision-pipeline-capstone/) | Build | Python | +| 17 | [自监督视觉——SimCLR、DINO、MAE](phases/04-computer-vision/17-self-supervised-vision/) | Build | Python | +| 18 | [开放词汇视觉——CLIP](phases/04-computer-vision/18-open-vocab-clip/) | Build | Python | +| 19 | [OCR 与文档理解](phases/04-computer-vision/19-ocr-document-understanding/) | Build | Python | +| 20 | [图像检索与度量学习](phases/04-computer-vision/20-image-retrieval-metric/) | Build | Python | +| 21 | [关键点检测与姿态估计](phases/04-computer-vision/21-keypoint-pose/) | Build | Python | +| 22 | [从零实现 3D 高斯泼溅](phases/04-computer-vision/22-3d-gaussian-splatting/) | Build | Python | +| 23 | [扩散 Transformer 与整流流（Rectified Flow）](phases/04-computer-vision/23-diffusion-transformers-rectified-flow/) | Build | Python | +| 24 | [SAM 3 与开放词汇分割](phases/04-computer-vision/24-sam3-open-vocab-segmentation/) | Build | Python | +| 25 | [视觉语言模型（ViT-MLP-LLM）](phases/04-computer-vision/25-vision-language-models/) | Build | Python | +| 26 | [单目深度与几何估计](phases/04-computer-vision/26-monocular-depth/) | Build | Python | +| 27 | [多目标跟踪与视频记忆](phases/04-computer-vision/27-multi-object-tracking/) | Build | Python | +| 28 | [世界模型与视频扩散](phases/04-computer-vision/28-world-models-video-diffusion/) | Build | Python |
-Phase 5 — NLP: Foundations to Advanced  29 lessons  Language is the interface to intelligence. +阶段 5 — NLP：从基础到进阶  29 lessons  语言是通往智能的接口。
-| # | Lesson | Type | Lang | +| # | 课程 | 类型 | 语言 | |:---:|--------|:----:|------| -| 01 | [Text Processing: Tokenization, Stemming, Lemmatization](phases/05-nlp-foundations-to-advanced/01-text-processing/) | Build | Python | -| 02 | [Bag of Words, TF-IDF & Text Representation](phases/05-nlp-foundations-to-advanced/02-bag-of-words-tfidf/) | Build | Python | -| 03 | [Word Embeddings: Word2Vec from Scratch](phases/05-nlp-foundations-to-advanced/03-word-embeddings-word2vec/) | Build | Python | -| 04 | [GloVe, FastText & Subword Embeddings](phases/05-nlp-foundations-to-advanced/04-glove-fasttext-subword/) | Build | Python | -| 05 | [Sentiment Analysis](phases/05-nlp-foundations-to-advanced/05-sentiment-analysis/) | Build | Python | -| 06 | [Named Entity Recognition (NER)](phases/05-nlp-foundations-to-advanced/06-named-entity-recognition/) | Build | Python | -| 07 | [POS Tagging & Syntactic Parsing](phases/05-nlp-foundations-to-advanced/07-pos-tagging-parsing/) | Build | Python | -| 08 | [Text Classification — CNNs & RNNs for Text](phases/05-nlp-foundations-to-advanced/08-cnns-rnns-for-text/) | Build | Python | -| 09 | [Sequence-to-Sequence Models](phases/05-nlp-foundations-to-advanced/09-sequence-to-sequence/) | Build | Python | -| 10 | [Attention Mechanism — The Breakthrough](phases/05-nlp-foundations-to-advanced/10-attention-mechanism/) | Build | Python | -| 11 | [Machine Translation](phases/05-nlp-foundations-to-advanced/11-machine-translation/) | Build | Python | -| 12 | [Text Summarization](phases/05-nlp-foundations-to-advanced/12-text-summarization/) | Build | Python | -| 13 | [Question Answering Systems](phases/05-nlp-foundations-to-advanced/13-question-answering/) | Build | Python | -| 14 | [Information Retrieval & Search](phases/05-nlp-foundations-to-advanced/14-information-retrieval-search/) | Build | Python | -| 15 | [Topic Modeling: LDA, BERTopic](phases/05-nlp-foundations-to-advanced/15-topic-modeling/) | Build | Python | -| 16 | [Text Generation](phases/05-nlp-foundations-to-advanced/16-text-generation-pre-transformer/) | Build | Python | -| 17 | [Chatbots: Rule-Based to Neural](phases/05-nlp-foundations-to-advanced/17-chatbots-rule-to-neural/) | Build | Python | -| 18 | [Multilingual NLP](phases/05-nlp-foundations-to-advanced/18-multilingual-nlp/) | Build | Python | -| 19 | [Subword Tokenization: BPE, WordPiece, Unigram, SentencePiece](phases/05-nlp-foundations-to-advanced/19-subword-tokenization/) | Learn | Python | -| 20 | [Structured Outputs & Constrained Decoding](phases/05-nlp-foundations-to-advanced/20-structured-outputs-constrained-decoding/) | Build | Python | -| 21 | [NLI & Textual Entailment](phases/05-nlp-foundations-to-advanced/21-nli-textual-entailment/) | Learn | Python | -| 22 | [Embedding Models Deep Dive](phases/05-nlp-foundations-to-advanced/22-embedding-models-deep-dive/) | Learn | Python | -| 23 | [Chunking Strategies for RAG](phases/05-nlp-foundations-to-advanced/23-chunking-strategies-rag/) | Build | Python | -| 24 | [Coreference Resolution](phases/05-nlp-foundations-to-advanced/24-coreference-resolution/) | Learn | Python | -| 25 | [Entity Linking & Disambiguation](phases/05-nlp-foundations-to-advanced/25-entity-linking/) | Build | Python | -| 26 | [Relation Extraction & Knowledge Graph Construction](phases/05-nlp-foundations-to-advanced/26-relation-extraction-kg/) | Build | Python | -| 27 | [LLM Evaluation: RAGAS, DeepEval, G-Eval](phases/05-nlp-foundations-to-advanced/27-llm-evaluation-frameworks/) | Build | Python | -| 28 | [Long-Context Evaluation: NIAH, RULER, LongBench, MRCR](phases/05-nlp-foundations-to-advanced/28-long-context-evaluation/) | Learn | Python | -| 29 | [Dialogue State Tracking](phases/05-nlp-foundations-to-advanced/29-dialogue-state-tracking/) | Build | Python | +| 01 | [文本处理：分词、词干提取与词形还原](phases/05-nlp-foundations-to-advanced/01-text-processing/) | Build | Python | +| 02 | [词袋模型、TF-IDF 与文本表示](phases/05-nlp-foundations-to-advanced/02-bag-of-words-tfidf/) | Build | Python | +| 03 | [词嵌入：从零实现 Word2Vec](phases/05-nlp-foundations-to-advanced/03-word-embeddings-word2vec/) | Build | Python | +| 04 | [GloVe、FastText 与子词嵌入](phases/05-nlp-foundations-to-advanced/04-glove-fasttext-subword/) | Build | Python | +| 05 | [情感分析](phases/05-nlp-foundations-to-advanced/05-sentiment-analysis/) | Build | Python | +| 06 | [命名实体识别（NER）](phases/05-nlp-foundations-to-advanced/06-named-entity-recognition/) | Build | Python | +| 07 | [词性标注与句法分析](phases/05-nlp-foundations-to-advanced/07-pos-tagging-parsing/) | Build | Python | +| 08 | [文本分类——用于文本的 CNN 与 RNN](phases/05-nlp-foundations-to-advanced/08-cnns-rnns-for-text/) | Build | Python | +| 09 | [序列到序列模型](phases/05-nlp-foundations-to-advanced/09-sequence-to-sequence/) | Build | Python | +| 10 | [注意力机制——突破性进展](phases/05-nlp-foundations-to-advanced/10-attention-mechanism/) | Build | Python | +| 11 | [机器翻译](phases/05-nlp-foundations-to-advanced/11-machine-translation/) | Build | Python | +| 12 | [文本摘要](phases/05-nlp-foundations-to-advanced/12-text-summarization/) | Build | Python | +| 13 | [问答系统](phases/05-nlp-foundations-to-advanced/13-question-answering/) | Build | Python | +| 14 | [信息检索与搜索](phases/05-nlp-foundations-to-advanced/14-information-retrieval-search/) | Build | Python | +| 15 | [主题建模：LDA、BERTopic](phases/05-nlp-foundations-to-advanced/15-topic-modeling/) | Build | Python | +| 16 | [文本生成](phases/05-nlp-foundations-to-advanced/16-text-generation-pre-transformer/) | Build | Python | +| 17 | [聊天机器人：从规则驱动到神经网络](phases/05-nlp-foundations-to-advanced/17-chatbots-rule-to-neural/) | Build | Python | +| 18 | [多语言 NLP](phases/05-nlp-foundations-to-advanced/18-multilingual-nlp/) | Build | Python | +| 19 | [子词分词：BPE、WordPiece、Unigram、SentencePiece](phases/05-nlp-foundations-to-advanced/19-subword-tokenization/) | Learn | Python | +| 20 | [结构化输出与约束解码](phases/05-nlp-foundations-to-advanced/20-structured-outputs-constrained-decoding/) | Build | Python | +| 21 | [自然语言推理（NLI）与文本蕴含](phases/05-nlp-foundations-to-advanced/21-nli-textual-entailment/) | Learn | Python | +| 22 | [嵌入模型深入解析](phases/05-nlp-foundations-to-advanced/22-embedding-models-deep-dive/) | Learn | Python | +| 23 | [RAG 分块策略](phases/05-nlp-foundations-to-advanced/23-chunking-strategies-rag/) | Build | Python | +| 24 | [共指消解](phases/05-nlp-foundations-to-advanced/24-coreference-resolution/) | Learn | Python | +| 25 | [实体链接与消歧](phases/05-nlp-foundations-to-advanced/25-entity-linking/) | Build | Python | +| 26 | [关系抽取与知识图谱构建](phases/05-nlp-foundations-to-advanced/26-relation-extraction-kg/) | Build | Python | +| 27 | [LLM 评估：RAGAS、DeepEval、G-Eval](phases/05-nlp-foundations-to-advanced/27-llm-evaluation-frameworks/) | Build | Python | +| 28 | [长上下文评估：NIAH、RULER、LongBench、MRCR](phases/05-nlp-foundations-to-advanced/28-long-context-evaluation/) | Learn | Python | +| 29 | [对话状态跟踪](phases/05-nlp-foundations-to-advanced/29-dialogue-state-tracking/) | Build | Python |
-Phase 6 — Speech & Audio  17 lessons  Hear, understand, speak. +阶段 6 — 语音与音频（Speech & Audio）  17 lessons  听、理解、说。
-| # | Lesson | Type | Lang | +| # | 课程 | 类型 | 语言 | |:---:|--------|:----:|------| -| 01 | [Audio Fundamentals: Waveforms, Sampling, FFT](phases/06-speech-and-audio/01-audio-fundamentals) | Learn | Python | -| 02 | [Spectrograms, Mel Scale & Audio Features](phases/06-speech-and-audio/02-spectrograms-mel-features) | Build | Python | -| 03 | [Audio Classification](phases/06-speech-and-audio/03-audio-classification) | Build | Python | -| 04 | [Speech Recognition (ASR)](phases/06-speech-and-audio/04-speech-recognition-asr) | Build | Python | -| 05 | [Whisper: Architecture & Fine-Tuning](phases/06-speech-and-audio/05-whisper-architecture-finetuning) | Build | Python | -| 06 | [Speaker Recognition & Verification](phases/06-speech-and-audio/06-speaker-recognition-verification) | Build | Python | -| 07 | [Text-to-Speech (TTS)](phases/06-speech-and-audio/07-text-to-speech) | Build | Python | -| 08 | [Voice Cloning & Voice Conversion](phases/06-speech-and-audio/08-voice-cloning-conversion) | Build | Python | -| 09 | [Music Generation](phases/06-speech-and-audio/09-music-generation) | Build | Python | -| 10 | [Audio-Language Models](phases/06-speech-and-audio/10-audio-language-models) | Build | Python | -| 11 | [Real-Time Audio Processing](phases/06-speech-and-audio/11-real-time-audio-processing) | Build | Python | -| 12 | [Build a Voice Assistant Pipeline](phases/06-speech-and-audio/12-voice-assistant-pipeline) | Build | Python | -| 13 | [Neural Audio Codecs — EnCodec, SNAC, Mimi, DAC](phases/06-speech-and-audio/13-neural-audio-codecs) | Learn | Python | -| 14 | [Voice Activity Detection & Turn-Taking](phases/06-speech-and-audio/14-voice-activity-detection-turn-taking) | Build | Python | -| 15 | [Streaming Speech-to-Speech — Moshi, Hibiki](phases/06-speech-and-audio/15-streaming-speech-to-speech-moshi-hibiki) | Learn | Python | -| 16 | [Voice Anti-Spoofing & Audio Watermarking](phases/06-speech-and-audio/16-anti-spoofing-audio-watermarking) | Build | Python | -| 17 | [Audio Evaluation — WER, MOS, MMAU, Leaderboards](phases/06-speech-and-audio/17-audio-evaluation-metrics) | Learn | Python | +| 01 | [音频基础：波形、采样与 FFT](phases/06-speech-and-audio/01-audio-fundamentals) | Learn | Python | +| 02 | [频谱图、Mel 刻度与音频特征](phases/06-speech-and-audio/02-spectrograms-mel-features) | Build | Python | +| 03 | [音频分类](phases/06-speech-and-audio/03-audio-classification) | Build | Python | +| 04 | [语音识别（ASR）](phases/06-speech-and-audio/04-speech-recognition-asr) | Build | Python | +| 05 | [Whisper：架构与微调](phases/06-speech-and-audio/05-whisper-architecture-finetuning) | Build | Python | +| 06 | [说话人识别与验证](phases/06-speech-and-audio/06-speaker-recognition-verification) | Build | Python | +| 07 | [文本转语音（TTS）](phases/06-speech-and-audio/07-text-to-speech) | Build | Python | +| 08 | [声音克隆与音色转换](phases/06-speech-and-audio/08-voice-cloning-conversion) | Build | Python | +| 09 | [音乐生成](phases/06-speech-and-audio/09-music-generation) | Build | Python | +| 10 | [音频语言模型](phases/06-speech-and-audio/10-audio-language-models) | Build | Python | +| 11 | [实时音频处理](phases/06-speech-and-audio/11-real-time-audio-processing) | Build | Python | +| 12 | [构建语音助手流水线](phases/06-speech-and-audio/12-voice-assistant-pipeline) | Build | Python | +| 13 | [神经音频编解码器——EnCodec、SNAC、Mimi、DAC](phases/06-speech-and-audio/13-neural-audio-codecs) | Learn | Python | +| 14 | [语音活动检测与话轮转换](phases/06-speech-and-audio/14-voice-activity-detection-turn-taking) | Build | Python | +| 15 | [流式语音到语音——Moshi、Hibiki](phases/06-speech-and-audio/15-streaming-speech-to-speech-moshi-hibiki) | Learn | Python | +| 16 | [语音反欺骗与音频水印](phases/06-speech-and-audio/16-anti-spoofing-audio-watermarking) | Build | Python | +| 17 | [音频评估——WER、MOS、MMAU 与排行榜](phases/06-speech-and-audio/17-audio-evaluation-metrics) | Learn | Python |
-Phase 7 — Transformers Deep Dive  14 lessons  The architecture that changed everything. +Phase 7 — Transformers 深度剖析  14 lessons  改变一切的架构。
-| # | Lesson | Type | Lang | +| # | 课程 | 类型 | 语言 | |:---:|--------|:----:|------| -| 01 | [Why Transformers: The Problems with RNNs](phases/07-transformers-deep-dive/01-why-transformers/) | Learn | Python | -| 02 | [Self-Attention from Scratch](phases/07-transformers-deep-dive/02-self-attention-from-scratch/) | Build | Python | -| 03 | [Multi-Head Attention](phases/07-transformers-deep-dive/03-multi-head-attention/) | Build | Python | -| 04 | [Positional Encoding: Sinusoidal, RoPE, ALiBi](phases/07-transformers-deep-dive/04-positional-encoding/) | Build | Python | -| 05 | [The Full Transformer: Encoder + Decoder](phases/07-transformers-deep-dive/05-full-transformer/) | Build | Python | -| 06 | [BERT — Masked Language Modeling](phases/07-transformers-deep-dive/06-bert-masked-language-modeling/) | Build | Python | -| 07 | [GPT — Causal Language Modeling](phases/07-transformers-deep-dive/07-gpt-causal-language-modeling/) | Build | Python | -| 08 | [T5, BART — Encoder-Decoder Models](phases/07-transformers-deep-dive/08-t5-bart-encoder-decoder/) | Learn | Python | -| 09 | [Vision Transformers (ViT)](phases/07-transformers-deep-dive/09-vision-transformers/) | Build | Python | -| 10 | [Audio Transformers — Whisper Architecture](phases/07-transformers-deep-dive/10-audio-transformers-whisper/) | Learn | Python | -| 11 | [Mixture of Experts (MoE)](phases/07-transformers-deep-dive/11-mixture-of-experts/) | Build | Python | -| 12 | [KV Cache, Flash Attention & Inference Optimization](phases/07-transformers-deep-dive/12-kv-cache-flash-attention/) | Build | Python | -| 13 | [Scaling Laws](phases/07-transformers-deep-dive/13-scaling-laws/) | Learn | Python | -| 14 | [Build a Transformer from Scratch](phases/07-transformers-deep-dive/14-build-a-transformer-capstone/) | Build | Python | -| 15 | [Attention Variants — Sliding Window, Sparse, Differential](phases/07-transformers-deep-dive/15-attention-variants/) | Build | Python | -| 16 | [Speculative Decoding — Draft, Verify, Repeat](phases/07-transformers-deep-dive/16-speculative-decoding/) | Build | Python | +| 01 | [为何选择 Transformers：RNN 的问题](phases/07-transformers-deep-dive/01-why-transformers/) | 学习 | Python | +| 02 | [从零实现自注意力（Self-Attention）](phases/07-transformers-deep-dive/02-self-attention-from-scratch/) | 构建 | Python | +| 03 | [多头注意力（Multi-Head Attention）](phases/07-transformers-deep-dive/03-multi-head-attention/) | 构建 | Python | +| 04 | [位置编码：Sinusoidal、RoPE、ALiBi](phases/07-transformers-deep-dive/04-positional-encoding/) | 构建 | Python | +| 05 | [完整 Transformer：编码器 + 解码器](phases/07-transformers-deep-dive/05-full-transformer/) | 构建 | Python | +| 06 | [BERT — 掩码语言建模（Masked Language Modeling）](phases/07-transformers-deep-dive/06-bert-masked-language-modeling/) | 构建 | Python | +| 07 | [GPT — 因果语言建模（Causal Language Modeling）](phases/07-transformers-deep-dive/07-gpt-causal-language-modeling/) | 构建 | Python | +| 08 | [T5、BART — 编码器-解码器模型](phases/07-transformers-deep-dive/08-t5-bart-encoder-decoder/) | 学习 | Python | +| 09 | [视觉 Transformer（ViT）](phases/07-transformers-deep-dive/09-vision-transformers/) | 构建 | Python | +| 10 | [音频 Transformer — Whisper 架构](phases/07-transformers-deep-dive/10-audio-transformers-whisper/) | 学习 | Python | +| 11 | [混合专家（MoE）](phases/07-transformers-deep-dive/11-mixture-of-experts/) | 构建 | Python | +| 12 | [KV Cache、Flash Attention 与推理优化](phases/07-transformers-deep-dive/12-kv-cache-flash-attention/) | 构建 | Python | +| 13 | [缩放定律（Scaling Laws）](phases/07-transformers-deep-dive/13-scaling-laws/) | 学习 | Python | +| 14 | [从零构建 Transformer](phases/07-transformers-deep-dive/14-build-a-transformer-capstone/) | 构建 | Python | +| 15 | [注意力变体 — 滑动窗口、稀疏、差分](phases/07-transformers-deep-dive/15-attention-variants/) | 构建 | Python | +| 16 | [推测解码（Speculative Decoding）— 起草、验证、重复](phases/07-transformers-deep-dive/16-speculative-decoding/) | 构建 | Python |
-Phase 8 — Generative AI  14 lessons  Create images, video, audio, 3D, and more. +Phase 8 — 生成式 AI  14 lessons  生成图像、视频、音频、3D 等内容。
-| # | Lesson | Type | Lang | +| # | 课程 | 类型 | 语言 | |:---:|--------|:----:|------| -| 01 | [Generative Models: Taxonomy & History](phases/08-generative-ai/01-generative-models-taxonomy-history/) | Learn | Python | -| 02 | [Autoencoders & VAE](phases/08-generative-ai/02-autoencoders-vae/) | Build | Python | -| 03 | [GANs: Generator vs Discriminator](phases/08-generative-ai/03-gans-generator-discriminator/) | Build | Python | -| 04 | [Conditional GANs & Pix2Pix](phases/08-generative-ai/04-conditional-gans-pix2pix/) | Build | Python | -| 05 | [StyleGAN](phases/08-generative-ai/05-stylegan/) | Build | Python | -| 06 | [Diffusion Models — DDPM from Scratch](phases/08-generative-ai/06-diffusion-ddpm-from-scratch/) | Build | Python | -| 07 | [Latent Diffusion & Stable Diffusion](phases/08-generative-ai/07-latent-diffusion-stable-diffusion/) | Build | Python | -| 08 | [ControlNet, LoRA & Conditioning](phases/08-generative-ai/08-controlnet-lora-conditioning/) | Build | Python | -| 09 | [Inpainting, Outpainting & Editing](phases/08-generative-ai/09-inpainting-outpainting-editing/) | Build | Python | -| 10 | [Video Generation](phases/08-generative-ai/10-video-generation/) | Build | Python | -| 11 | [Audio Generation](phases/08-generative-ai/11-audio-generation/) | Build | Python | -| 12 | [3D Generation](phases/08-generative-ai/12-3d-generation/) | Build | Python | -| 13 | [Flow Matching & Rectified Flows](phases/08-generative-ai/13-flow-matching-rectified-flows/) | Build | Python | -| 14 | [Evaluation: FID, CLIP Score](phases/08-generative-ai/14-evaluation-fid-clip-score/) | Build | Python | -| 19 | [Visual Autoregressive Modeling (VAR): Next-Scale Prediction](phases/08-generative-ai/19-visual-autoregressive-var/) | Build | Python | +| 01 | [生成模型：分类与历史](phases/08-generative-ai/01-generative-models-taxonomy-history/) | 学习 | Python | +| 02 | [自编码器与 VAE](phases/08-generative-ai/02-autoencoders-vae/) | 构建 | Python | +| 03 | [GAN：生成器与判别器](phases/08-generative-ai/03-gans-generator-discriminator/) | 构建 | Python | +| 04 | [条件 GAN 与 Pix2Pix](phases/08-generative-ai/04-conditional-gans-pix2pix/) | 构建 | Python | +| 05 | [StyleGAN](phases/08-generative-ai/05-stylegan/) | 构建 | Python | +| 06 | [扩散模型 — 从零实现 DDPM](phases/08-generative-ai/06-diffusion-ddpm-from-scratch/) | 构建 | Python | +| 07 | [潜在扩散与 Stable Diffusion](phases/08-generative-ai/07-latent-diffusion-stable-diffusion/) | 构建 | Python | +| 08 | [ControlNet、LoRA 与条件控制](phases/08-generative-ai/08-controlnet-lora-conditioning/) | 构建 | Python | +| 09 | [图像修复、外扩与编辑](phases/08-generative-ai/09-inpainting-outpainting-editing/) | 构建 | Python | +| 10 | [视频生成](phases/08-generative-ai/10-video-generation/) | 构建 | Python | +| 11 | [音频生成](phases/08-generative-ai/11-audio-generation/) | 构建 | Python | +| 12 | [3D 生成](phases/08-generative-ai/12-3d-generation/) | 构建 | Python | +| 13 | [流匹配（Flow Matching）与整流流（Rectified Flows）](phases/08-generative-ai/13-flow-matching-rectified-flows/) | 构建 | Python | +| 14 | [评估：FID、CLIP Score](phases/08-generative-ai/14-evaluation-fid-clip-score/) | 构建 | Python | +| 19 | [视觉自回归建模（VAR）：下一尺度预测](phases/08-generative-ai/19-visual-autoregressive-var/) | 构建 | Python |
-Phase 9 — Reinforcement Learning  12 lessons  The foundation of RLHF and game-playing AI. +Phase 9 — 强化学习  12 lessons  RLHF 与博弈 AI 的基础。
-| # | Lesson | Type | Lang | +| # | 课程 | 类型 | 语言 | |:---:|--------|:----:|------| -| 01 | [MDPs, States, Actions & Rewards](phases/09-reinforcement-learning/01-mdps-states-actions-rewards/) | Learn | Python | -| 02 | [Dynamic Programming](phases/09-reinforcement-learning/02-dynamic-programming/) | Build | Python | -| 03 | [Monte Carlo Methods](phases/09-reinforcement-learning/03-monte-carlo-methods/) | Build | Python | -| 04 | [Q-Learning, SARSA](phases/09-reinforcement-learning/04-q-learning-sarsa/) | Build | Python | -| 05 | [Deep Q-Networks (DQN)](phases/09-reinforcement-learning/05-dqn/) | Build | Python | -| 06 | [Policy Gradients — REINFORCE](phases/09-reinforcement-learning/06-policy-gradients-reinforce/) | Build | Python | -| 07 | [Actor-Critic — A2C, A3C](phases/09-reinforcement-learning/07-actor-critic-a2c-a3c/) | Build | Python | -| 08 | [PPO](phases/09-reinforcement-learning/08-ppo/) | Build | Python | -| 09 | [Reward Modeling & RLHF](phases/09-reinforcement-learning/09-reward-modeling-rlhf/) | Build | Python | -| 10 | [Multi-Agent RL](phases/09-reinforcement-learning/10-multi-agent-rl/) | Build | Python | -| 11 | [Sim-to-Real Transfer](phases/09-reinforcement-learning/11-sim-to-real-transfer/) | Build | Python | -| 12 | [RL for Games](phases/09-reinforcement-learning/12-rl-for-games/) | Build | Python | +| 01 | [MDP、状态、动作与奖励](phases/09-reinforcement-learning/01-mdps-states-actions-rewards/) | 学习 | Python | +| 02 | [动态规划](phases/09-reinforcement-learning/02-dynamic-programming/) | 构建 | Python | +| 03 | [蒙特卡洛方法](phases/09-reinforcement-learning/03-monte-carlo-methods/) | 构建 | Python | +| 04 | [Q-Learning、SARSA](phases/09-reinforcement-learning/04-q-learning-sarsa/) | 构建 | Python | +| 05 | [深度 Q 网络（DQN）](phases/09-reinforcement-learning/05-dqn/) | 构建 | Python | +| 06 | [策略梯度 — REINFORCE](phases/09-reinforcement-learning/06-policy-gradients-reinforce/) | 构建 | Python | +| 07 | [Actor-Critic — A2C、A3C](phases/09-reinforcement-learning/07-actor-critic-a2c-a3c/) | 构建 | Python | +| 08 | [PPO](phases/09-reinforcement-learning/08-ppo/) | 构建 | Python | +| 09 | [奖励建模与 RLHF](phases/09-reinforcement-learning/09-reward-modeling-rlhf/) | 构建 | Python | +| 10 | [多智能体强化学习](phases/09-reinforcement-learning/10-multi-agent-rl/) | 构建 | Python | +| 11 | [仿真到现实迁移（Sim-to-Real Transfer）](phases/09-reinforcement-learning/11-sim-to-real-transfer/) | 构建 | Python | +| 12 | [面向游戏的强化学习](phases/09-reinforcement-learning/12-rl-for-games/) | 构建 | Python |
-Phase 10 — LLMs from Scratch  22 lessons  Build, train, and understand large language models. +Phase 10 — 从零构建大语言模型  22 lessons  构建、训练并理解大语言模型。
-| # | Lesson | Type | Lang | +| # | 课程 | 类型 | 语言 | |:---:|--------|:----:|------| -| 01 | [Tokenizers: BPE, WordPiece, SentencePiece](phases/10-llms-from-scratch/01-tokenizers/) | Build | Python, Rust | -| 02 | [Building a Tokenizer from Scratch](phases/10-llms-from-scratch/02-building-a-tokenizer/) | Build | Python | -| 03 | [Data Pipelines for Pre-Training](phases/10-llms-from-scratch/03-data-pipelines/) | Build | Python | -| 04 | [Pre-Training a Mini GPT (124M)](phases/10-llms-from-scratch/04-pre-training-mini-gpt/) | Build | Python | -| 05 | [Distributed Training, FSDP, DeepSpeed](phases/10-llms-from-scratch/05-scaling-distributed/) | Build | Python | -| 06 | [Instruction Tuning — SFT](phases/10-llms-from-scratch/06-instruction-tuning-sft/) | Build | Python | -| 07 | [RLHF — Reward Model + PPO](phases/10-llms-from-scratch/07-rlhf/) | Build | Python | -| 08 | [DPO — Direct Preference Optimization](phases/10-llms-from-scratch/08-dpo/) | Build | Python | -| 09 | [Constitutional AI & Self-Improvement](phases/10-llms-from-scratch/09-constitutional-ai-self-improvement/) | Build | Python | -| 10 | [Evaluation — Benchmarks, Evals](phases/10-llms-from-scratch/10-evaluation/) | Build | Python | -| 11 | [Quantization: INT8, GPTQ, AWQ, GGUF](phases/10-llms-from-scratch/11-quantization/) | Build | Python | -| 12 | [Inference Optimization](phases/10-llms-from-scratch/12-inference-optimization/) | Build | Python | -| 13 | [Building a Complete LLM Pipeline](phases/10-llms-from-scratch/13-building-complete-llm-pipeline/) | Build | Python | -| 14 | [Open Models: Architecture Walkthroughs](phases/10-llms-from-scratch/14-open-models-architecture-walkthroughs/) | Learn | Python | -| 15 | [Speculative Decoding and EAGLE-3](phases/10-llms-from-scratch/15-speculative-decoding-eagle3/) | Build | Python | -| 16 | [Differential Attention (V2)](phases/10-llms-from-scratch/16-differential-attention-v2/) | Build | Python | -| 17 | [Native Sparse Attention (DeepSeek NSA)](phases/10-llms-from-scratch/17-native-sparse-attention/) | Build | Python | -| 18 | [Multi-Token Prediction (MTP)](phases/10-llms-from-scratch/18-multi-token-prediction/) | Build | Python | -| 19 | [DualPipe Parallelism](phases/10-llms-from-scratch/19-dualpipe-parallelism/) | Learn | Python | -| 20 | [DeepSeek-V3 Architecture Walkthrough](phases/10-llms-from-scratch/20-deepseek-v3-walkthrough/) | Learn | Python | -| 21 | [Jamba — Hybrid SSM-Transformer](phases/10-llms-from-scratch/21-jamba-hybrid-ssm-transformer/) | Learn | Python | -| 22 | [Async and Hogwild! Inference](phases/10-llms-from-scratch/22-async-hogwild-inference/) | Build | Python | -| 25 | [Speculative Decoding and EAGLE](phases/10-llms-from-scratch/25-speculative-decoding/) | Build | Python | -| 34 | [Gradient Checkpointing and Activation Recomputation](phases/10-llms-from-scratch/34-gradient-checkpointing/) | Build | Python | +| 01 | [分词器：BPE、WordPiece、SentencePiece](phases/10-llms-from-scratch/01-tokenizers/) | 构建 | Python, Rust | +| 02 | [从零构建分词器](phases/10-llms-from-scratch/02-building-a-tokenizer/) | 构建 | Python | +| 03 | [预训练数据流水线](phases/10-llms-from-scratch/03-data-pipelines/) | 构建 | Python | +| 04 | [预训练 Mini GPT（124M）](phases/10-llms-from-scratch/04-pre-training-mini-gpt/) | 构建 | Python | +| 05 | [分布式训练、FSDP、DeepSpeed](phases/10-llms-from-scratch/05-scaling-distributed/) | 构建 | Python | +| 06 | [指令微调 — SFT](phases/10-llms-from-scratch/06-instruction-tuning-sft/) | 构建 | Python | +| 07 | [RLHF — 奖励模型 + PPO](phases/10-llms-from-scratch/07-rlhf/) | 构建 | Python | +| 08 | [DPO — 直接偏好优化（Direct Preference Optimization）](phases/10-llms-from-scratch/08-dpo/) | 构建 | Python | +| 09 | [宪法 AI（Constitutional AI）与自我改进](phases/10-llms-from-scratch/09-constitutional-ai-self-improvement/) | 构建 | Python | +| 10 | [评估 — 基准测试与评测](phases/10-llms-from-scratch/10-evaluation/) | 构建 | Python | +| 11 | [量化：INT8、GPTQ、AWQ、GGUF](phases/10-llms-from-scratch/11-quantization/) | 构建 | Python | +| 12 | [推理优化](phases/10-llms-from-scratch/12-inference-optimization/) | 构建 | Python | +| 13 | [构建完整的 LLM 流水线](phases/10-llms-from-scratch/13-building-complete-llm-pipeline/) | 构建 | Python | +| 14 | [开放模型：架构详解](phases/10-llms-from-scratch/14-open-models-architecture-walkthroughs/) | 学习 | Python | +| 15 | [推测解码与 EAGLE-3](phases/10-llms-from-scratch/15-speculative-decoding-eagle3/) | 构建 | Python | +| 16 | [差分注意力（V2）](phases/10-llms-from-scratch/16-differential-attention-v2/) | 构建 | Python | +| 17 | [原生稀疏注意力（DeepSeek NSA）](phases/10-llms-from-scratch/17-native-sparse-attention/) | 构建 | Python | +| 18 | [多 token 预测（MTP）](phases/10-llms-from-scratch/18-multi-token-prediction/) | 构建 | Python | +| 19 | [DualPipe 并行](phases/10-llms-from-scratch/19-dualpipe-parallelism/) | 学习 | Python | +| 20 | [DeepSeek-V3 架构详解](phases/10-llms-from-scratch/20-deepseek-v3-walkthrough/) | 学习 | Python | +| 21 | [Jamba — 混合 SSM-Transformer](phases/10-llms-from-scratch/21-jamba-hybrid-ssm-transformer/) | 学习 | Python | +| 22 | [异步与 Hogwild! 推理](phases/10-llms-from-scratch/22-async-hogwild-inference/) | 构建 | Python | +| 25 | [推测解码与 EAGLE](phases/10-llms-from-scratch/25-speculative-decoding/) | 构建 | Python | +| 34 | [梯度检查点与激活重计算](phases/10-llms-from-scratch/34-gradient-checkpointing/) | 构建 | Python |
-Phase 11 — LLM Engineering  17 lessons  Put LLMs to work in production. +Phase 11 — LLM 工程  17 lessons  让 LLM 投入生产环境。
-| # | Lesson | Type | Lang | +| # | 课程 | 类型 | 语言 | |:---:|--------|:----:|------| -| 01 | [Prompt Engineering: Techniques & Patterns](phases/11-llm-engineering/01-prompt-engineering/) | Build | Python | -| 02 | [Few-Shot, CoT, Tree-of-Thought](phases/11-llm-engineering/02-few-shot-cot/) | Build | Python | -| 03 | [Structured Outputs](phases/11-llm-engineering/03-structured-outputs/) | Build | Python | -| 04 | [Embeddings & Vector Representations](phases/11-llm-engineering/04-embeddings/) | Build | Python | -| 05 | [Context Engineering](phases/11-llm-engineering/05-context-engineering/) | Build | Python | -| 06 | [RAG: Retrieval-Augmented Generation](phases/11-llm-engineering/06-rag/) | Build | Python | -| 07 | [Advanced RAG: Chunking, Reranking](phases/11-llm-engineering/07-advanced-rag/) | Build | Python | -| 08 | [Fine-Tuning with LoRA & QLoRA](phases/11-llm-engineering/08-fine-tuning-lora/) | Build | Python | -| 09 | [Function Calling & Tool Use](phases/11-llm-engineering/09-function-calling/) | Build | Python | -| 10 | [Evaluation & Testing](phases/11-llm-engineering/10-evaluation/) | Build | Python | -| 11 | [Caching, Rate Limiting & Cost](phases/11-llm-engineering/11-caching-cost/) | Build | Python | -| 12 | [Guardrails & Safety](phases/11-llm-engineering/12-guardrails/) | Build | Python | -| 13 | [Building a Production LLM App](phases/11-llm-engineering/13-production-app/) | Build | Python | -| 14 | [Model Context Protocol (MCP)](phases/11-llm-engineering/14-model-context-protocol/) | Build | Python | -| 15 | [Prompt Caching & Context Caching](phases/11-llm-engineering/15-prompt-caching/) | Build | Python | -| 16 | [LangGraph: State Machines for Agents](phases/11-llm-engineering/16-langgraph-state-machines/) | Build | Python | -| 17 | [Agent Framework Tradeoffs](phases/11-llm-engineering/17-agent-framework-tradeoffs/) | Learn | Python | +| 01 | [提示工程：技术与模式](phases/11-llm-engineering/01-prompt-engineering/) | Build | Python | +| 02 | [少样本、思维链（CoT）与思维树（Tree-of-Thought）](phases/11-llm-engineering/02-few-shot-cot/) | Build | Python | +| 03 | [结构化输出](phases/11-llm-engineering/03-structured-outputs/) | Build | Python | +| 04 | [嵌入与向量表示](phases/11-llm-engineering/04-embeddings/) | Build | Python | +| 05 | [上下文工程](phases/11-llm-engineering/05-context-engineering/) | Build | Python | +| 06 | [RAG：检索增强生成（Retrieval-Augmented Generation）](phases/11-llm-engineering/06-rag/) | Build | Python | +| 07 | [高级 RAG：分块与重排序](phases/11-llm-engineering/07-advanced-rag/) | Build | Python | +| 08 | [使用 LoRA 与 QLoRA 进行微调](phases/11-llm-engineering/08-fine-tuning-lora/) | Build | Python | +| 09 | [函数调用与工具使用](phases/11-llm-engineering/09-function-calling/) | Build | Python | +| 10 | [评估与测试](phases/11-llm-engineering/10-evaluation/) | Build | Python | +| 11 | [缓存、速率限制与成本](phases/11-llm-engineering/11-caching-cost/) | Build | Python | +| 12 | [护栏与安全](phases/11-llm-engineering/12-guardrails/) | Build | Python | +| 13 | [构建生产级 LLM 应用](phases/11-llm-engineering/13-production-app/) | Build | Python | +| 14 | [模型上下文协议（Model Context Protocol, MCP）](phases/11-llm-engineering/14-model-context-protocol/) | Build | Python | +| 15 | [提示缓存与上下文缓存](phases/11-llm-engineering/15-prompt-caching/) | Build | Python | +| 16 | [LangGraph：智能体的状态机](phases/11-llm-engineering/16-langgraph-state-machines/) | Build | Python | +| 17 | [智能体框架权衡](phases/11-llm-engineering/17-agent-framework-tradeoffs/) | Learn | Python |
-Phase 12 — Multimodal AI  25 lessons  See, hear, read, and reason across modalities — from ViT patches to computer-use agents. +Phase 12 — 多模态 AI  25 lessons  跨模态地看、听、读与推理——从 ViT 图像块到计算机使用智能体。
-| # | Lesson | Type | Lang | +| # | 课程 | 类型 | 语言 | |:---:|--------|:----:|------| -| 01 | [Vision Transformers and the Patch-Token Primitive](phases/12-multimodal-ai/01-vision-transformer-patch-tokens/) | Learn | Python | -| 02 | [CLIP and Contrastive Vision-Language Pretraining](phases/12-multimodal-ai/02-clip-contrastive-pretraining/) | Build | Python | -| 03 | [BLIP-2 Q-Former as Modality Bridge](phases/12-multimodal-ai/03-blip2-qformer-bridge/) | Build | Python | -| 04 | [Flamingo and Gated Cross-Attention](phases/12-multimodal-ai/04-flamingo-gated-cross-attention/) | Learn | Python | -| 05 | [LLaVA and Visual Instruction Tuning](phases/12-multimodal-ai/05-llava-visual-instruction-tuning/) | Build | Python | -| 06 | [Any-Resolution Vision — Patch-n'-Pack and NaFlex](phases/12-multimodal-ai/06-any-resolution-patch-n-pack/) | Build | Python | -| 07 | [Open-Weight VLM Recipes: What Actually Matters](phases/12-multimodal-ai/07-open-weight-vlm-recipes/) | Learn | Python | -| 08 | [LLaVA-OneVision: Single, Multi, Video](phases/12-multimodal-ai/08-llava-onevision-single-multi-video/) | Build | Python | -| 09 | [Qwen-VL Family and Dynamic-FPS Video](phases/12-multimodal-ai/09-qwen-vl-family-dynamic-fps/) | Learn | Python | -| 10 | [InternVL3 Native Multimodal Pretraining](phases/12-multimodal-ai/10-internvl3-native-multimodal/) | Learn | Python | -| 11 | [Chameleon Early-Fusion Token-Only](phases/12-multimodal-ai/11-chameleon-early-fusion-tokens/) | Build | Python | -| 12 | [Emu3 Next-Token Prediction for Generation](phases/12-multimodal-ai/12-emu3-next-token-for-generation/) | Learn | Python | -| 13 | [Transfusion Autoregressive + Diffusion](phases/12-multimodal-ai/13-transfusion-autoregressive-diffusion/) | Build | Python | -| 14 | [Show-o Discrete-Diffusion Unified](phases/12-multimodal-ai/14-show-o-discrete-diffusion-unified/) | Learn | Python | -| 15 | [Janus-Pro Decoupled Encoders](phases/12-multimodal-ai/15-janus-pro-decoupled-encoders/) | Build | Python | -| 16 | [MIO Any-to-Any Streaming](phases/12-multimodal-ai/16-mio-any-to-any-streaming/) | Learn | Python | -| 17 | [Video-Language Temporal Grounding](phases/12-multimodal-ai/17-video-language-temporal-grounding/) | Build | Python | -| 18 | [Long-Video at Million-Token Context](phases/12-multimodal-ai/18-long-video-million-token/) | Build | Python | -| 19 | [Audio-Language Models: Whisper to AF3](phases/12-multimodal-ai/19-audio-language-whisper-to-af3/) | Build | Python | -| 20 | [Omni Models: Thinker-Talker Streaming](phases/12-multimodal-ai/20-omni-models-thinker-talker/) | Build | Python | -| 21 | [Embodied VLAs: RT-2, OpenVLA, π0, GR00T](phases/12-multimodal-ai/21-embodied-vlas-openvla-pi0-groot/) | Learn | Python | -| 22 | [Document and Diagram Understanding](phases/12-multimodal-ai/22-document-diagram-understanding/) | Build | Python | -| 23 | [ColPali Vision-Native Document RAG](phases/12-multimodal-ai/23-colpali-vision-native-rag/) | Build | Python | -| 24 | [Multimodal RAG and Cross-Modal Retrieval](phases/12-multimodal-ai/24-multimodal-rag-cross-modal/) | Build | Python | -| 25 | [Multimodal Agents and Computer-Use (Capstone)](phases/12-multimodal-ai/25-multimodal-agents-computer-use/) | Build | Python | +| 01 | [视觉 Transformer 与 Patch-Token 原语](phases/12-multimodal-ai/01-vision-transformer-patch-tokens/) | Learn | Python | +| 02 | [CLIP 与对比式视觉-语言预训练](phases/12-multimodal-ai/02-clip-contrastive-pretraining/) | Build | Python | +| 03 | [BLIP-2 Q-Former 作为模态桥梁](phases/12-multimodal-ai/03-blip2-qformer-bridge/) | Build | Python | +| 04 | [Flamingo 与门控交叉注意力](phases/12-multimodal-ai/04-flamingo-gated-cross-attention/) | Learn | Python | +| 05 | [LLaVA 与视觉指令微调](phases/12-multimodal-ai/05-llava-visual-instruction-tuning/) | Build | Python | +| 06 | [任意分辨率视觉——Patch-n'-Pack 与 NaFlex](phases/12-multimodal-ai/06-any-resolution-patch-n-pack/) | Build | Python | +| 07 | [开放权重 VLM 配方：什么真正重要](phases/12-multimodal-ai/07-open-weight-vlm-recipes/) | Learn | Python | +| 08 | [LLaVA-OneVision：单图、多图与视频](phases/12-multimodal-ai/08-llava-onevision-single-multi-video/) | Build | Python | +| 09 | [Qwen-VL 系列与动态 FPS 视频](phases/12-multimodal-ai/09-qwen-vl-family-dynamic-fps/) | Learn | Python | +| 10 | [InternVL3 原生多模态预训练](phases/12-multimodal-ai/10-internvl3-native-multimodal/) | Learn | Python | +| 11 | [Chameleon 早期融合纯 Token 方案](phases/12-multimodal-ai/11-chameleon-early-fusion-tokens/) | Build | Python | +| 12 | [Emu3 用于生成的下一 Token 预测](phases/12-multimodal-ai/12-emu3-next-token-for-generation/) | Learn | Python | +| 13 | [Transfusion：自回归 + 扩散](phases/12-multimodal-ai/13-transfusion-autoregressive-diffusion/) | Build | Python | +| 14 | [Show-o 离散扩散统一模型](phases/12-multimodal-ai/14-show-o-discrete-diffusion-unified/) | Learn | Python | +| 15 | [Janus-Pro 解耦编码器](phases/12-multimodal-ai/15-janus-pro-decoupled-encoders/) | Build | Python | +| 16 | [MIO 任意到任意流式传输](phases/12-multimodal-ai/16-mio-any-to-any-streaming/) | Learn | Python | +| 17 | [视频-语言时间定位](phases/12-multimodal-ai/17-video-language-temporal-grounding/) | Build | Python | +| 18 | [百万 Token 上下文下的长视频](phases/12-multimodal-ai/18-long-video-million-token/) | Build | Python | +| 19 | [音频-语言模型：从 Whisper 到 AF3](phases/12-multimodal-ai/19-audio-language-whisper-to-af3/) | Build | Python | +| 20 | [Omni 模型：Thinker-Talker 流式架构](phases/12-multimodal-ai/20-omni-models-thinker-talker/) | Build | Python | +| 21 | [具身 VLA：RT-2、OpenVLA、π0、GR00T](phases/12-multimodal-ai/21-embodied-vlas-openvla-pi0-groot/) | Learn | Python | +| 22 | [文档与图表理解](phases/12-multimodal-ai/22-document-diagram-understanding/) | Build | Python | +| 23 | [ColPali 视觉原生文档 RAG](phases/12-multimodal-ai/23-colpali-vision-native-rag/) | Build | Python | +| 24 | [多模态 RAG 与跨模态检索](phases/12-multimodal-ai/24-multimodal-rag-cross-modal/) | Build | Python | +| 25 | [多模态智能体与计算机使用（毕业项目）](phases/12-multimodal-ai/25-multimodal-agents-computer-use/) | Build | Python |
-Phase 13 — Tools & Protocols  23 lessons  The interfaces between AI and the real world. +Phase 13 — 工具与协议  23 lessons  AI 与现实世界之间的接口。
-| # | Lesson | Type | Lang | +| # | 课程 | 类型 | 语言 | |:---:|--------|:----:|------| -| 01 | [The Tool Interface](phases/13-tools-and-protocols/01-the-tool-interface/) | Learn | Python | -| 02 | [Function Calling Deep Dive](phases/13-tools-and-protocols/02-function-calling-deep-dive/) | Build | Python | -| 03 | [Parallel and Streaming Tool Calls](phases/13-tools-and-protocols/03-parallel-and-streaming-tool-calls/) | Build | Python | -| 04 | [Structured Output](phases/13-tools-and-protocols/04-structured-output/) | Build | Python | -| 05 | [Tool Schema Design](phases/13-tools-and-protocols/05-tool-schema-design/) | Learn | Python | -| 06 | [MCP Fundamentals](phases/13-tools-and-protocols/06-mcp-fundamentals/) | Learn | Python | -| 07 | [Building an MCP Server](phases/13-tools-and-protocols/07-building-an-mcp-server/) | Build | Python | -| 08 | [Building an MCP Client](phases/13-tools-and-protocols/08-building-an-mcp-client/) | Build | Python | -| 09 | [MCP Transports](phases/13-tools-and-protocols/09-mcp-transports/) | Learn | Python | -| 10 | [MCP Resources and Prompts](phases/13-tools-and-protocols/10-mcp-resources-and-prompts/) | Build | Python | -| 11 | [MCP Sampling](phases/13-tools-and-protocols/11-mcp-sampling/) | Build | Python | -| 12 | [MCP Roots and Elicitation](phases/13-tools-and-protocols/12-mcp-roots-and-elicitation/) | Build | Python | -| 13 | [MCP Async Tasks](phases/13-tools-and-protocols/13-mcp-async-tasks/) | Build | Python | -| 14 | [MCP Apps](phases/13-tools-and-protocols/14-mcp-apps/) | Build | Python | -| 15 | [MCP Security I — Tool Poisoning](phases/13-tools-and-protocols/15-mcp-security-tool-poisoning/) | Learn | Python | -| 16 | [MCP Security II — OAuth 2.1](phases/13-tools-and-protocols/16-mcp-security-oauth-2-1/) | Build | Python | -| 17 | [MCP Gateways and Registries](phases/13-tools-and-protocols/17-mcp-gateways-and-registries/) | Learn | Python | -| 18 | [MCP Auth in Production — Enrollment, JWKS Refresh, Audience Pinning](phases/13-tools-and-protocols/18-mcp-auth-production/) | Build | Python | -| 19 | [A2A Protocol](phases/13-tools-and-protocols/19-a2a-protocol/) | Build | Python | +| 01 | [工具接口](phases/13-tools-and-protocols/01-the-tool-interface/) | Learn | Python | +| 02 | [函数调用深度解析](phases/13-tools-and-protocols/02-function-calling-deep-dive/) | Build | Python | +| 03 | [并行与流式工具调用](phases/13-tools-and-protocols/03-parallel-and-streaming-tool-calls/) | Build | Python | +| 04 | [结构化输出](phases/13-tools-and-protocols/04-structured-output/) | Build | Python | +| 05 | [工具模式设计](phases/13-tools-and-protocols/05-tool-schema-design/) | Learn | Python | +| 06 | [MCP 基础](phases/13-tools-and-protocols/06-mcp-fundamentals/) | Learn | Python | +| 07 | [构建 MCP 服务器](phases/13-tools-and-protocols/07-building-an-mcp-server/) | Build | Python | +| 08 | [构建 MCP 客户端](phases/13-tools-and-protocols/08-building-an-mcp-client/) | Build | Python | +| 09 | [MCP 传输层](phases/13-tools-and-protocols/09-mcp-transports/) | Learn | Python | +| 10 | [MCP 资源与提示](phases/13-tools-and-protocols/10-mcp-resources-and-prompts/) | Build | Python | +| 11 | [MCP 采样](phases/13-tools-and-protocols/11-mcp-sampling/) | Build | Python | +| 12 | [MCP Roots 与引导（Elicitation）](phases/13-tools-and-protocols/12-mcp-roots-and-elicitation/) | Build | Python | +| 13 | [MCP 异步任务](phases/13-tools-and-protocols/13-mcp-async-tasks/) | Build | Python | +| 14 | [MCP 应用](phases/13-tools-and-protocols/14-mcp-apps/) | Build | Python | +| 15 | [MCP 安全 I——工具投毒](phases/13-tools-and-protocols/15-mcp-security-tool-poisoning/) | Learn | Python | +| 16 | [MCP 安全 II——OAuth 2.1](phases/13-tools-and-protocols/16-mcp-security-oauth-2-1/) | Build | Python | +| 17 | [MCP 网关与注册表](phases/13-tools-and-protocols/17-mcp-gateways-and-registries/) | Learn | Python | +| 18 | [生产环境中的 MCP 认证——注册、JWKS 刷新与受众固定（Audience Pinning）](phases/13-tools-and-protocols/18-mcp-auth-production/) | Build | Python | +| 19 | [A2A 协议](phases/13-tools-and-protocols/19-a2a-protocol/) | Build | Python | | 20 | [OpenTelemetry GenAI](phases/13-tools-and-protocols/20-opentelemetry-genai/) | Build | Python | -| 21 | [LLM Routing Layer](phases/13-tools-and-protocols/21-llm-routing-layer/) | Learn | Python | -| 22 | [Skills and Agent SDKs](phases/13-tools-and-protocols/22-skills-and-agent-sdks/) | Learn | Python | -| 23 | [Capstone — Tool Ecosystem](phases/13-tools-and-protocols/23-capstone-tool-ecosystem/) | Build | Python | +| 21 | [LLM 路由层](phases/13-tools-and-protocols/21-llm-routing-layer/) | Learn | Python | +| 22 | [Skills 与智能体 SDK](phases/13-tools-and-protocols/22-skills-and-agent-sdks/) | Learn | Python | +| 23 | [毕业项目——工具生态系统](phases/13-tools-and-protocols/23-capstone-tool-ecosystem/) | Build | Python |
-Phase 14 — Agent Engineering  42 lessons  Build agents from first principles — loop, memory, planning, frameworks, benchmarks, production, workbench. +Phase 14 — 智能体工程（Agent Engineering）  42 lessons  从第一性原理构建智能体——循环、记忆、规划、框架、基准测试、生产部署与工作台。
| # | Lesson | Type | Lang | |:---:|--------|:----:|------| -| 01 | [The Agent Loop](phases/14-agent-engineering/01-the-agent-loop/) | Build | Python | -| 02 | [ReWOO and Plan-and-Execute](phases/14-agent-engineering/02-rewoo-plan-and-execute/) | Build | Python | -| 03 | [Reflexion and Verbal Reinforcement Learning](phases/14-agent-engineering/03-reflexion-verbal-rl/) | Build | Python | -| 04 | [Tree of Thoughts and LATS](phases/14-agent-engineering/04-tree-of-thoughts-lats/) | Build | Python | -| 05 | [Self-Refine and CRITIC](phases/14-agent-engineering/05-self-refine-and-critic/) | Build | Python | -| 06 | [Tool Use and Function Calling](phases/14-agent-engineering/06-tool-use-and-function-calling/) | Build | Python | -| 07 | [Memory — Virtual Context and MemGPT](phases/14-agent-engineering/07-memory-virtual-context-memgpt/) | Build | Python | -| 08 | [Memory Blocks and Sleep-Time Compute](phases/14-agent-engineering/08-memory-blocks-sleep-time-compute/) | Build | Python | -| 09 | [Hybrid Memory — Mem0 Vector + Graph + KV](phases/14-agent-engineering/09-hybrid-memory-mem0/) | Build | Python | -| 10 | [Skill Libraries and Lifelong Learning — Voyager](phases/14-agent-engineering/10-skill-libraries-voyager/) | Build | Python | -| 11 | [Planning with HTN and Evolutionary Search](phases/14-agent-engineering/11-planning-htn-and-evolutionary/) | Build | Python | -| 12 | [Anthropic's Workflow Patterns](phases/14-agent-engineering/12-anthropic-workflow-patterns/) | Build | Python | -| 13 | [LangGraph — Stateful Graphs and Durable Execution](phases/14-agent-engineering/13-langgraph-stateful-graphs/) | Build | Python | -| 14 | [AutoGen v0.4 — Actor Model](phases/14-agent-engineering/14-autogen-actor-model/) | Build | Python | -| 15 | [CrewAI — Role-Based Crews and Flows](phases/14-agent-engineering/15-crewai-role-based-crews/) | Build | Python | -| 16 | [OpenAI Agents SDK — Handoffs, Guardrails, Tracing](phases/14-agent-engineering/16-openai-agents-sdk/) | Build | Python | -| 17 | [Claude Agent SDK — Subagents and Session Store](phases/14-agent-engineering/17-claude-agent-sdk/) | Build | Python | -| 18 | [Agno and Mastra — Production Runtimes](phases/14-agent-engineering/18-agno-and-mastra-runtimes/) | Learn | Python | -| 19 | [Benchmarks — SWE-bench, GAIA, AgentBench](phases/14-agent-engineering/19-benchmarks-swebench-gaia/) | Learn | Python | -| 20 | [Benchmarks — WebArena and OSWorld](phases/14-agent-engineering/20-benchmarks-webarena-osworld/) | Learn | Python | -| 21 | [Computer Use — Claude, OpenAI CUA, Gemini](phases/14-agent-engineering/21-computer-use-agents/) | Build | Python | -| 22 | [Voice Agents — Pipecat and LiveKit](phases/14-agent-engineering/22-voice-agents-pipecat-livekit/) | Build | Python | -| 23 | [OpenTelemetry GenAI Semantic Conventions](phases/14-agent-engineering/23-otel-genai-conventions/) | Build | Python | -| 24 | [Agent Observability — Langfuse, Phoenix, Opik](phases/14-agent-engineering/24-agent-observability-platforms/) | Learn | Python | -| 25 | [Multi-Agent Debate and Collaboration](phases/14-agent-engineering/25-multi-agent-debate/) | Build | Python | -| 26 | [Failure Modes — Why Agents Break](phases/14-agent-engineering/26-failure-modes-agentic/) | Build | Python | -| 27 | [Prompt Injection and the PVE Defense](phases/14-agent-engineering/27-prompt-injection-defense/) | Build | Python | -| 28 | [Orchestration Patterns — Supervisor, Swarm, Hierarchical](phases/14-agent-engineering/28-orchestration-patterns/) | Build | Python | -| 29 | [Production Runtimes — Queue, Event, Cron](phases/14-agent-engineering/29-production-runtimes/) | Learn | Python | -| 30 | [Eval-Driven Agent Development](phases/14-agent-engineering/30-eval-driven-agent-development/) | Build | Python | -| 31 | [Agent Workbench: Why Capable Models Still Fail](phases/14-agent-engineering/31-agent-workbench-why-models-fail/) | Learn | Python | -| 32 | [The Minimal Agent Workbench](phases/14-agent-engineering/32-minimal-agent-workbench/) | Build | Python | -| 33 | [Agent Instructions as Executable Constraints](phases/14-agent-engineering/33-instructions-as-executable-constraints/) | Build | Python | -| 34 | [Repo Memory and Durable State](phases/14-agent-engineering/34-repo-memory-and-state/) | Build | Python | -| 35 | [Initialization Scripts for Agents](phases/14-agent-engineering/35-initialization-scripts/) | Build | Python | -| 36 | [Scope Contracts and Task Boundaries](phases/14-agent-engineering/36-scope-contracts/) | Build | Python | -| 37 | [Runtime Feedback Loops](phases/14-agent-engineering/37-runtime-feedback-loops/) | Build | Python | -| 38 | [Verification Gates](phases/14-agent-engineering/38-verification-gates/) | Build | Python | -| 39 | [Reviewer Agent: Separate Builder from Marker](phases/14-agent-engineering/39-reviewer-agent/) | Build | Python | -| 40 | [Multi-Session Handoff](phases/14-agent-engineering/40-multi-session-handoff/) | Build | Python | -| 41 | [The Workbench on a Real Repo](phases/14-agent-engineering/41-workbench-for-real-repos/) | Build | Python | -| 42 | [Capstone: Ship a Reusable Agent Workbench Pack](phases/14-agent-engineering/42-agent-workbench-capstone/) | Build | Python | +| 01 | [智能体循环（The Agent Loop）](phases/14-agent-engineering/01-the-agent-loop/) | Build | Python | +| 02 | [ReWOO 与 Plan-and-Execute](phases/14-agent-engineering/02-rewoo-plan-and-execute/) | Build | Python | +| 03 | [Reflexion 与言语强化学习（Verbal Reinforcement Learning）](phases/14-agent-engineering/03-reflexion-verbal-rl/) | Build | Python | +| 04 | [思维树（Tree of Thoughts）与 LATS](phases/14-agent-engineering/04-tree-of-thoughts-lats/) | Build | Python | +| 05 | [Self-Refine 与 CRITIC](phases/14-agent-engineering/05-self-refine-and-critic/) | Build | Python | +| 06 | [工具使用与函数调用（Tool Use and Function Calling）](phases/14-agent-engineering/06-tool-use-and-function-calling/) | Build | Python | +| 07 | [记忆——虚拟上下文与 MemGPT](phases/14-agent-engineering/07-memory-virtual-context-memgpt/) | Build | Python | +| 08 | [记忆块与休眠期计算（Sleep-Time Compute）](phases/14-agent-engineering/08-memory-blocks-sleep-time-compute/) | Build | Python | +| 09 | [混合记忆——Mem0 向量 + 图 + KV](phases/14-agent-engineering/09-hybrid-memory-mem0/) | Build | Python | +| 10 | [技能库与终身学习——Voyager](phases/14-agent-engineering/10-skill-libraries-voyager/) | Build | Python | +| 11 | [基于 HTN 与进化搜索的规划](phases/14-agent-engineering/11-planning-htn-and-evolutionary/) | Build | Python | +| 12 | [Anthropic 工作流模式](phases/14-agent-engineering/12-anthropic-workflow-patterns/) | Build | Python | +| 13 | [LangGraph——有状态图与持久化执行](phases/14-agent-engineering/13-langgraph-stateful-graphs/) | Build | Python | +| 14 | [AutoGen v0.4——Actor 模型](phases/14-agent-engineering/14-autogen-actor-model/) | Build | Python | +| 15 | [CrewAI——基于角色的 Crew 与 Flow](phases/14-agent-engineering/15-crewai-role-based-crews/) | Build | Python | +| 16 | [OpenAI Agents SDK——交接、护栏与追踪](phases/14-agent-engineering/16-openai-agents-sdk/) | Build | Python | +| 17 | [Claude Agent SDK——子智能体与会话存储](phases/14-agent-engineering/17-claude-agent-sdk/) | Build | Python | +| 18 | [Agno 与 Mastra——生产运行时](phases/14-agent-engineering/18-agno-and-mastra-runtimes/) | Learn | Python | +| 19 | [基准测试——SWE-bench、GAIA、AgentBench](phases/14-agent-engineering/19-benchmarks-swebench-gaia/) | Learn | Python | +| 20 | [基准测试——WebArena 与 OSWorld](phases/14-agent-engineering/20-benchmarks-webarena-osworld/) | Learn | Python | +| 21 | [计算机使用——Claude、OpenAI CUA、Gemini](phases/14-agent-engineering/21-computer-use-agents/) | Build | Python | +| 22 | [语音智能体——Pipecat 与 LiveKit](phases/14-agent-engineering/22-voice-agents-pipecat-livekit/) | Build | Python | +| 23 | [OpenTelemetry GenAI 语义约定](phases/14-agent-engineering/23-otel-genai-conventions/) | Build | Python | +| 24 | [智能体可观测性——Langfuse、Phoenix、Opik](phases/14-agent-engineering/24-agent-observability-platforms/) | Learn | Python | +| 25 | [多智能体辩论与协作](phases/14-agent-engineering/25-multi-agent-debate/) | Build | Python | +| 26 | [失效模式——智能体为何崩溃](phases/14-agent-engineering/26-failure-modes-agentic/) | Build | Python | +| 27 | [提示注入与 PVE 防御](phases/14-agent-engineering/27-prompt-injection-defense/) | Build | Python | +| 28 | [编排模式——Supervisor、Swarm、分层](phases/14-agent-engineering/28-orchestration-patterns/) | Build | Python | +| 29 | [生产运行时——队列、事件、Cron](phases/14-agent-engineering/29-production-runtimes/) | Learn | Python | +| 30 | [评估驱动的智能体开发](phases/14-agent-engineering/30-eval-driven-agent-development/) | Build | Python | +| 31 | [智能体工作台：能力强的模型为何仍会失败](phases/14-agent-engineering/31-agent-workbench-why-models-fail/) | Learn | Python | +| 32 | [最小智能体工作台](phases/14-agent-engineering/32-minimal-agent-workbench/) | Build | Python | +| 33 | [将智能体指令作为可执行约束](phases/14-agent-engineering/33-instructions-as-executable-constraints/) | Build | Python | +| 34 | [仓库记忆与持久化状态](phases/14-agent-engineering/34-repo-memory-and-state/) | Build | Python | +| 35 | [智能体初始化脚本](phases/14-agent-engineering/35-initialization-scripts/) | Build | Python | +| 36 | [范围契约与任务边界](phases/14-agent-engineering/36-scope-contracts/) | Build | Python | +| 37 | [运行时反馈循环](phases/14-agent-engineering/37-runtime-feedback-loops/) | Build | Python | +| 38 | [验证关卡](phases/14-agent-engineering/38-verification-gates/) | Build | Python | +| 39 | [审查智能体：将构建者与标注者分离](phases/14-agent-engineering/39-reviewer-agent/) | Build | Python | +| 40 | [多会话交接](phases/14-agent-engineering/40-multi-session-handoff/) | Build | Python | +| 41 | [在真实仓库上的工作台](phases/14-agent-engineering/41-workbench-for-real-repos/) | Build | Python | +| 42 | [毕业项目：交付可复用的智能体工作台包](phases/14-agent-engineering/42-agent-workbench-capstone/) | Build | Python | -Each Phase 14 workbench lesson (31-42) ships a `mission.md` briefing the agent before it opens the full lesson docs. +Phase 14 中每个工作台课时（31–42）都会在打开完整课时文档前，向智能体提供一份 `mission.md` 简报。
-Phase 15 — Autonomous Systems  22 lessons  Long-horizon agents, self-improvement, and the 2026 safety stack. +Phase 15 — 自主系统（Autonomous Systems）  22 lessons  长程智能体、自我改进与 2026 安全栈。
| # | Lesson | Type | Lang | |:---:|--------|:----:|------| -| 01 | [From Chatbots to Long-Horizon Agents (METR)](phases/15-autonomous-systems/01-long-horizon-agents/) | Learn | Python | -| 02 | [STaR, V-STaR, Quiet-STaR: Self-Taught Reasoning](phases/15-autonomous-systems/02-star-family-reasoning/) | Learn | Python | -| 03 | [AlphaEvolve: Evolutionary Coding Agents](phases/15-autonomous-systems/03-alphaevolve-evolutionary-coding/) | Learn | Python | -| 04 | [Darwin Gödel Machine: Self-Modifying Agents](phases/15-autonomous-systems/04-darwin-godel-machine/) | Learn | Python | -| 05 | [AI Scientist v2: Workshop-Level Research](phases/15-autonomous-systems/05-ai-scientist-v2/) | Learn | Python | -| 06 | [Automated Alignment Research (Anthropic AAR)](phases/15-autonomous-systems/06-automated-alignment-research/) | Learn | Python | -| 07 | [Recursive Self-Improvement: Capability vs Alignment](phases/15-autonomous-systems/07-recursive-self-improvement/) | Learn | Python | -| 08 | [Bounded Self-Improvement Designs](phases/15-autonomous-systems/08-bounded-self-improvement/) | Learn | Python | -| 09 | [Autonomous Coding Agent Landscape (SWE-bench, CodeAct)](phases/15-autonomous-systems/09-coding-agent-landscape/) | Learn | Python | -| 10 | [Claude Code Permission Modes and Auto Mode](phases/15-autonomous-systems/10-claude-code-permission-modes/) | Learn | Python | -| 11 | [Browser Agents and Indirect Prompt Injection](phases/15-autonomous-systems/11-browser-agents/) | Learn | Python | -| 12 | [Durable Execution for Long-Running Agents](phases/15-autonomous-systems/12-durable-execution/) | Learn | Python | -| 13 | [Action Budgets, Iteration Caps, Cost Governors](phases/15-autonomous-systems/13-cost-governors/) | Learn | Python | -| 14 | [Kill Switches, Circuit Breakers, Canary Tokens](phases/15-autonomous-systems/14-kill-switches-canaries/) | Learn | Python | -| 15 | [HITL: Propose-Then-Commit](phases/15-autonomous-systems/15-propose-then-commit/) | Learn | Python | -| 16 | [Checkpoints and Rollback](phases/15-autonomous-systems/16-checkpoints-rollback/) | Learn | Python | -| 17 | [Constitutional AI and Rule Overrides](phases/15-autonomous-systems/17-constitutional-ai/) | Learn | Python | -| 18 | [Llama Guard and Input/Output Classification](phases/15-autonomous-systems/18-llama-guard/) | Learn | Python | -| 19 | [Anthropic Responsible Scaling Policy v3.0](phases/15-autonomous-systems/19-anthropic-rsp/) | Learn | Python | -| 20 | [OpenAI Preparedness Framework and DeepMind FSF](phases/15-autonomous-systems/20-openai-preparedness-deepmind-fsf/) | Learn | Python | -| 21 | [METR Time Horizons and External Evaluation](phases/15-autonomous-systems/21-metr-external-evaluation/) | Learn | Python | -| 22 | [CAIS, CAISI, and Societal-Scale Risk](phases/15-autonomous-systems/22-cais-caisi-societal-risk/) | Learn | Python | +| 01 | [从聊天机器人到长程智能体（METR）](phases/15-autonomous-systems/01-long-horizon-agents/) | Learn | Python | +| 02 | [STaR、V-STaR、Quiet-STaR：自教推理](phases/15-autonomous-systems/02-star-family-reasoning/) | Learn | Python | +| 03 | [AlphaEvolve：进化式编码智能体](phases/15-autonomous-systems/03-alphaevolve-evolutionary-coding/) | Learn | Python | +| 04 | [Darwin Gödel Machine：自修改智能体](phases/15-autonomous-systems/04-darwin-godel-machine/) | Learn | Python | +| 05 | [AI Scientist v2：工作坊级研究](phases/15-autonomous-systems/05-ai-scientist-v2/) | Learn | Python | +| 06 | [自动化对齐研究（Anthropic AAR）](phases/15-autonomous-systems/06-automated-alignment-research/) | Learn | Python | +| 07 | [递归自我改进：能力 vs 对齐](phases/15-autonomous-systems/07-recursive-self-improvement/) | Learn | Python | +| 08 | [有界自我改进设计](phases/15-autonomous-systems/08-bounded-self-improvement/) | Learn | Python | +| 09 | [自主编码智能体全景（SWE-bench、CodeAct）](phases/15-autonomous-systems/09-coding-agent-landscape/) | Learn | Python | +| 10 | [Claude Code 权限模式与自动模式](phases/15-autonomous-systems/10-claude-code-permission-modes/) | Learn | Python | +| 11 | [浏览器智能体与间接提示注入](phases/15-autonomous-systems/11-browser-agents/) | Learn | Python | +| 12 | [长运行智能体的持久化执行](phases/15-autonomous-systems/12-durable-execution/) | Learn | Python | +| 13 | [动作预算、迭代上限与成本管控](phases/15-autonomous-systems/13-cost-governors/) | Learn | Python | +| 14 | [终止开关、熔断器与金丝雀令牌](phases/15-autonomous-systems/14-kill-switches-canaries/) | Learn | Python | +| 15 | [HITL：先提议后提交](phases/15-autonomous-systems/15-propose-then-commit/) | Learn | Python | +| 16 | [检查点与回滚](phases/15-autonomous-systems/16-checkpoints-rollback/) | Learn | Python | +| 17 | [宪法式 AI 与规则覆盖](phases/15-autonomous-systems/17-constitutional-ai/) | Learn | Python | +| 18 | [Llama Guard 与输入/输出分类](phases/15-autonomous-systems/18-llama-guard/) | Learn | Python | +| 19 | [Anthropic 负责任扩展政策 v3.0](phases/15-autonomous-systems/19-anthropic-rsp/) | Learn | Python | +| 20 | [OpenAI 准备度框架与 DeepMind FSF](phases/15-autonomous-systems/20-openai-preparedness-deepmind-fsf/) | Learn | Python | +| 21 | [METR 时间跨度与外部评估](phases/15-autonomous-systems/21-metr-external-evaluation/) | Learn | Python | +| 22 | [CAIS、CAISI 与社会规模风险](phases/15-autonomous-systems/22-cais-caisi-societal-risk/) | Learn | Python |
-Phase 16 — Multi-Agent & Swarms  25 lessons  Coordination, emergence, and collective intelligence. +Phase 16 — 多智能体与群体智能（Swarms）  25 lessons  协调、涌现与集体智能。
-| # | Lesson | Type | Lang | +| # | 课程 | 类型 | 语言 | |:---:|--------|:----:|------| -| 01 | [Why Multi-Agent](phases/16-multi-agent-and-swarms/01-why-multi-agent/) | Learn | TypeScript | -| 02 | [FIPA-ACL Heritage and Speech Acts](phases/16-multi-agent-and-swarms/02-fipa-acl-heritage/) | Learn | Python | -| 03 | [Communication Protocols](phases/16-multi-agent-and-swarms/03-communication-protocols/) | Build | TypeScript | -| 04 | [The Multi-Agent Primitive Model](phases/16-multi-agent-and-swarms/04-primitive-model/) | Learn | Python | -| 05 | [Supervisor / Orchestrator-Worker Pattern](phases/16-multi-agent-and-swarms/05-supervisor-orchestrator-pattern/) | Build | Python | -| 06 | [Hierarchical Architecture and Decomposition Drift](phases/16-multi-agent-and-swarms/06-hierarchical-architecture/) | Learn | Python | -| 07 | [Society of Mind and Multi-Agent Debate](phases/16-multi-agent-and-swarms/07-society-of-mind-debate/) | Build | Python | -| 08 | [Role Specialization — Planner / Critic / Executor / Verifier](phases/16-multi-agent-and-swarms/08-role-specialization/) | Build | Python | -| 09 | [Parallel Swarm and Networked Architectures](phases/16-multi-agent-and-swarms/09-parallel-swarm-networks/) | Build | Python | -| 10 | [Group Chat and Speaker Selection](phases/16-multi-agent-and-swarms/10-group-chat-speaker-selection/) | Build | Python | -| 11 | [Handoffs and Routines (Stateless Orchestration)](phases/16-multi-agent-and-swarms/11-handoffs-and-routines/) | Build | Python | -| 12 | [A2A — The Agent-to-Agent Protocol](phases/16-multi-agent-and-swarms/12-a2a-protocol/) | Build | Python | -| 13 | [Shared Memory and Blackboard Patterns](phases/16-multi-agent-and-swarms/13-shared-memory-blackboard/) | Build | Python | -| 14 | [Consensus and Byzantine Fault Tolerance](phases/16-multi-agent-and-swarms/14-consensus-and-bft/) | Build | Python | -| 15 | [Voting, Self-Consistency, and Debate Topology](phases/16-multi-agent-and-swarms/15-voting-debate-topology/) | Build | Python | -| 16 | [Negotiation and Bargaining](phases/16-multi-agent-and-swarms/16-negotiation-bargaining/) | Build | Python | -| 17 | [Generative Agents and Emergent Simulation](phases/16-multi-agent-and-swarms/17-generative-agents-simulation/) | Build | Python | -| 18 | [Theory of Mind and Emergent Coordination](phases/16-multi-agent-and-swarms/18-theory-of-mind-coordination/) | Build | Python | -| 19 | [Swarm Optimization (PSO, ACO)](phases/16-multi-agent-and-swarms/19-swarm-optimization-pso-aco/) | Build | Python | -| 20 | [MARL — MADDPG, QMIX, MAPPO](phases/16-multi-agent-and-swarms/20-marl-maddpg-qmix-mappo/) | Learn | Python | -| 21 | [Agent Economies, Token Incentives, Reputation](phases/16-multi-agent-and-swarms/21-agent-economies/) | Learn | Python | -| 22 | [Production Scaling — Queues, Checkpoints, Durability](phases/16-multi-agent-and-swarms/22-production-scaling-queues-checkpoints/) | Build | Python | -| 23 | [Failure Modes — MAST, Groupthink, Monoculture](phases/16-multi-agent-and-swarms/23-failure-modes-mast-groupthink/) | Learn | Python | -| 24 | [Evaluation and Coordination Benchmarks](phases/16-multi-agent-and-swarms/24-evaluation-coordination-benchmarks/) | Learn | Python | -| 25 | [Case Studies and 2026 State of the Art](phases/16-multi-agent-and-swarms/25-case-studies-2026-sota/) | Learn | Python | +| 01 | [为何需要多智能体](phases/16-multi-agent-and-swarms/01-why-multi-agent/) | 学习 | TypeScript | +| 02 | [FIPA-ACL 传承与言语行为（Speech Acts）](phases/16-multi-agent-and-swarms/02-fipa-acl-heritage/) | 学习 | Python | +| 03 | [通信协议](phases/16-multi-agent-and-swarms/03-communication-protocols/) | 实践 | TypeScript | +| 04 | [多智能体原语模型](phases/16-multi-agent-and-swarms/04-primitive-model/) | 学习 | Python | +| 05 | [监督者 / 编排者-工作者模式](phases/16-multi-agent-and-swarms/05-supervisor-orchestrator-pattern/) | 实践 | Python | +| 06 | [层次化架构与分解漂移（Decomposition Drift）](phases/16-multi-agent-and-swarms/06-hierarchical-architecture/) | 学习 | Python | +| 07 | [心智社会与多智能体辩论](phases/16-multi-agent-and-swarms/07-society-of-mind-debate/) | 实践 | Python | +| 08 | [角色专业化 — 规划者 / 批评者 / 执行者 / 验证者](phases/16-multi-agent-and-swarms/08-role-specialization/) | 实践 | Python | +| 09 | [并行群体与网络化架构](phases/16-multi-agent-and-swarms/09-parallel-swarm-networks/) | 实践 | Python | +| 10 | [群聊与发言者选择](phases/16-multi-agent-and-swarms/10-group-chat-speaker-selection/) | 实践 | Python | +| 11 | [交接与例程（无状态编排）](phases/16-multi-agent-and-swarms/11-handoffs-and-routines/) | 实践 | Python | +| 12 | [A2A — 智能体间协议（Agent-to-Agent Protocol）](phases/16-multi-agent-and-swarms/12-a2a-protocol/) | 实践 | Python | +| 13 | [共享内存与黑板模式](phases/16-multi-agent-and-swarms/13-shared-memory-blackboard/) | 实践 | Python | +| 14 | [共识与拜占庭容错（Byzantine Fault Tolerance）](phases/16-multi-agent-and-swarms/14-consensus-and-bft/) | 实践 | Python | +| 15 | [投票、自洽性与辩论拓扑](phases/16-multi-agent-and-swarms/15-voting-debate-topology/) | 实践 | Python | +| 16 | [谈判与议价](phases/16-multi-agent-and-swarms/16-negotiation-bargaining/) | 实践 | Python | +| 17 | [生成式智能体与涌现仿真](phases/16-multi-agent-and-swarms/17-generative-agents-simulation/) | 实践 | Python | +| 18 | [心智理论（Theory of Mind）与涌现代际协调](phases/16-multi-agent-and-swarms/18-theory-of-mind-coordination/) | 实践 | Python | +| 19 | [群体优化（PSO、ACO）](phases/16-multi-agent-and-swarms/19-swarm-optimization-pso-aco/) | 实践 | Python | +| 20 | [MARL — MADDPG、QMIX、MAPPO](phases/16-multi-agent-and-swarms/20-marl-maddpg-qmix-mappo/) | 学习 | Python | +| 21 | [智能体经济、代币激励与声誉](phases/16-multi-agent-and-swarms/21-agent-economies/) | 学习 | Python | +| 22 | [生产级扩展 — 队列、检查点与持久性](phases/16-multi-agent-and-swarms/22-production-scaling-queues-checkpoints/) | 实践 | Python | +| 23 | [失效模式 — MAST、群体思维与单一文化](phases/16-multi-agent-and-swarms/23-failure-modes-mast-groupthink/) | 学习 | Python | +| 24 | [评估与协调基准](phases/16-multi-agent-and-swarms/24-evaluation-coordination-benchmarks/) | 学习 | Python | +| 25 | [案例研究与 2026 年最前沿进展](phases/16-multi-agent-and-swarms/25-case-studies-2026-sota/) | 学习 | Python |
-Phase 17 — Infrastructure & Production  28 lessons  Ship AI to the real world. +Phase 17 — 基础设施与生产部署  28 lessons  将 AI 交付到真实世界。
-| # | Lesson | Type | Lang | +| # | 课程 | 类型 | 语言 | |:---:|--------|:----:|------| -| 01 | [Managed LLM Platforms — Bedrock, Azure OpenAI, Vertex AI](phases/17-infrastructure-and-production/01-managed-llm-platforms/) | Learn | Python | -| 02 | [Inference Platform Economics — Fireworks, Together, Baseten, Modal](phases/17-infrastructure-and-production/02-inference-platform-economics/) | Learn | Python | -| 03 | [GPU Autoscaling on Kubernetes — Karpenter, KAI Scheduler](phases/17-infrastructure-and-production/03-gpu-autoscaling-kubernetes/) | Learn | Python | -| 04 | [vLLM Serving Internals — PagedAttention, Continuous Batching, Chunked Prefill](phases/17-infrastructure-and-production/04-vllm-serving-internals/) | Learn | Python | -| 05 | [EAGLE-3 Speculative Decoding in Production](phases/17-infrastructure-and-production/05-eagle3-speculative-decoding/) | Learn | Python | -| 06 | [SGLang and RadixAttention for Prefix-Heavy Workloads](phases/17-infrastructure-and-production/06-sglang-radixattention/) | Learn | Python | -| 07 | [TensorRT-LLM on Blackwell with FP8 and NVFP4](phases/17-infrastructure-and-production/07-tensorrt-llm-blackwell/) | Learn | Python | -| 08 | [Inference Metrics — TTFT, TPOT, ITL, Goodput, P99](phases/17-infrastructure-and-production/08-inference-metrics-goodput/) | Learn | Python | -| 09 | [Production Quantization — AWQ, GPTQ, GGUF, FP8, NVFP4](phases/17-infrastructure-and-production/09-production-quantization/) | Learn | Python | -| 10 | [Cold Start Mitigation for Serverless LLMs](phases/17-infrastructure-and-production/10-cold-start-mitigation/) | Learn | Python | -| 11 | [Multi-Region LLM Serving and KV Cache Locality](phases/17-infrastructure-and-production/11-multi-region-kv-locality/) | Learn | Python | -| 12 | [Edge Inference — ANE, Hexagon, WebGPU, Jetson](phases/17-infrastructure-and-production/12-edge-inference/) | Learn | Python | -| 13 | [LLM Observability Stack Selection](phases/17-infrastructure-and-production/13-llm-observability/) | Learn | Python | -| 14 | [Prompt Caching and Semantic Caching Economics](phases/17-infrastructure-and-production/14-prompt-semantic-caching/) | Learn | Python | -| 15 | [Batch APIs — the 50% Discount as Industry Standard](phases/17-infrastructure-and-production/15-batch-apis/) | Learn | Python | -| 16 | [Model Routing as a Cost-Reduction Primitive](phases/17-infrastructure-and-production/16-model-routing/) | Learn | Python | -| 17 | [Disaggregated Prefill/Decode — NVIDIA Dynamo and llm-d](phases/17-infrastructure-and-production/17-disaggregated-prefill-decode/) | Learn | Python | -| 18 | [vLLM Production Stack with LMCache KV Offloading](phases/17-infrastructure-and-production/18-vllm-production-stack-lmcache/) | Learn | Python | -| 19 | [AI Gateways — LiteLLM, Portkey, Kong, Bifrost](phases/17-infrastructure-and-production/19-ai-gateways/) | Learn | Python | -| 20 | [Shadow, Canary, and Progressive Deployment](phases/17-infrastructure-and-production/20-shadow-canary-progressive/) | Learn | Python | -| 21 | [A/B Testing LLM Features — GrowthBook and Statsig](phases/17-infrastructure-and-production/21-ab-testing-llm-features/) | Learn | Python | -| 22 | [Load Testing LLM APIs — k6, LLMPerf, GenAI-Perf](phases/17-infrastructure-and-production/22-load-testing-llm-apis/) | Build | Python | -| 23 | [SRE for AI — Multi-Agent Incident Response](phases/17-infrastructure-and-production/23-sre-for-ai/) | Learn | Python | -| 24 | [Chaos Engineering for LLM Production](phases/17-infrastructure-and-production/24-chaos-engineering-llm/) | Learn | Python | -| 25 | [Security — Secrets, PII Scrubbing, Audit Logs](phases/17-infrastructure-and-production/25-security-secrets-audit/) | Learn | Python | -| 26 | [Compliance — SOC 2, HIPAA, GDPR, EU AI Act, ISO 42001](phases/17-infrastructure-and-production/26-compliance-frameworks/) | Learn | Python | -| 27 | [FinOps for LLMs — Unit Economics and Multi-Tenant Attribution](phases/17-infrastructure-and-production/27-finops-llms/) | Learn | Python | -| 28 | [Self-Hosted Serving Selection — llama.cpp, Ollama, TGI, vLLM, SGLang](phases/17-infrastructure-and-production/28-self-hosted-serving-selection/) | Learn | Python | +| 01 | [托管式 LLM 平台 — Bedrock、Azure OpenAI、Vertex AI](phases/17-infrastructure-and-production/01-managed-llm-platforms/) | 学习 | Python | +| 02 | [推理平台经济学 — Fireworks、Together、Baseten、Modal](phases/17-infrastructure-and-production/02-inference-platform-economics/) | 学习 | Python | +| 03 | [Kubernetes 上的 GPU 自动扩缩 — Karpenter、KAI Scheduler](phases/17-infrastructure-and-production/03-gpu-autoscaling-kubernetes/) | 学习 | Python | +| 04 | [vLLM 服务内部机制 — PagedAttention、连续批处理（Continuous Batching）、分块预填充（Chunked Prefill）](phases/17-infrastructure-and-production/04-vllm-serving-internals/) | 学习 | Python | +| 05 | [生产环境中的 EAGLE-3 推测解码（Speculative Decoding）](phases/17-infrastructure-and-production/05-eagle3-speculative-decoding/) | 学习 | Python | +| 06 | [面向前缀密集型工作负载的 SGLang 与 RadixAttention](phases/17-infrastructure-and-production/06-sglang-radixattention/) | 学习 | Python | +| 07 | [在 Blackwell 上使用 FP8 与 NVFP4 的 TensorRT-LLM](phases/17-infrastructure-and-production/07-tensorrt-llm-blackwell/) | 学习 | Python | +| 08 | [推理指标 — TTFT、TPOT、ITL、Goodput、P99](phases/17-infrastructure-and-production/08-inference-metrics-goodput/) | 学习 | Python | +| 09 | [生产级量化 — AWQ、GPTQ、GGUF、FP8、NVFP4](phases/17-infrastructure-and-production/09-production-quantization/) | 学习 | Python | +| 10 | [无服务器 LLM 的冷启动缓解](phases/17-infrastructure-and-production/10-cold-start-mitigation/) | 学习 | Python | +| 11 | [多区域 LLM 服务与 KV 缓存局部性](phases/17-infrastructure-and-production/11-multi-region-kv-locality/) | 学习 | Python | +| 12 | [边缘推理 — ANE、Hexagon、WebGPU、Jetson](phases/17-infrastructure-and-production/12-edge-inference/) | 学习 | Python | +| 13 | [LLM 可观测性技术栈选型](phases/17-infrastructure-and-production/13-llm-observability/) | 学习 | Python | +| 14 | [提示缓存与语义缓存经济学](phases/17-infrastructure-and-production/14-prompt-semantic-caching/) | 学习 | Python | +| 15 | [批处理 API — 50% 折扣的行业标准](phases/17-infrastructure-and-production/15-batch-apis/) | 学习 | Python | +| 16 | [模型路由作为降本原语](phases/17-infrastructure-and-production/16-model-routing/) | 学习 | Python | +| 17 | [解耦式预填充/解码 — NVIDIA Dynamo 与 llm-d](phases/17-infrastructure-and-production/17-disaggregated-prefill-decode/) | 学习 | Python | +| 18 | [集成 LMCache KV 卸载的 vLLM 生产栈](phases/17-infrastructure-and-production/18-vllm-production-stack-lmcache/) | 学习 | Python | +| 19 | [AI 网关 — LiteLLM、Portkey、Kong、Bifrost](phases/17-infrastructure-and-production/19-ai-gateways/) | 学习 | Python | +| 20 | [影子、金丝雀与渐进式部署](phases/17-infrastructure-and-production/20-shadow-canary-progressive/) | 学习 | Python | +| 21 | [LLM 功能的 A/B 测试 — GrowthBook 与 Statsig](phases/17-infrastructure-and-production/21-ab-testing-llm-features/) | 学习 | Python | +| 22 | [LLM API 负载测试 — k6、LLMPerf、GenAI-Perf](phases/17-infrastructure-and-production/22-load-testing-llm-apis/) | 实践 | Python | +| 23 | [AI 的 SRE — 多智能体事件响应](phases/17-infrastructure-and-production/23-sre-for-ai/) | 学习 | Python | +| 24 | [LLM 生产的混沌工程](phases/17-infrastructure-and-production/24-chaos-engineering-llm/) | 学习 | Python | +| 25 | [安全 — 密钥、PII 脱敏与审计日志](phases/17-infrastructure-and-production/25-security-secrets-audit/) | 学习 | Python | +| 26 | [合规 — SOC 2、HIPAA、GDPR、EU AI Act、ISO 42001](phases/17-infrastructure-and-production/26-compliance-frameworks/) | 学习 | Python | +| 27 | [LLM 的 FinOps — 单位经济学与多租户归因](phases/17-infrastructure-and-production/27-finops-llms/) | 学习 | Python | +| 28 | [自托管服务选型 — llama.cpp、Ollama、TGI、vLLM、SGLang](phases/17-infrastructure-and-production/28-self-hosted-serving-selection/) | 学习 | Python |
-Phase 18 — Ethics, Safety & Alignment  30 lessons  Build AI that helps humanity. Not optional. +Phase 18 — 伦理、安全与对齐（Alignment）  30 lessons  构建造福人类的 AI。这不是可选项。
-| # | Lesson | Type | Lang | +| # | 课程 | 类型 | 语言 | |:---:|--------|:----:|------| -| 01 | [Instruction-Following as Alignment Signal](phases/18-ethics-safety-alignment/01-instruction-following-alignment-signal/) | Learn | Python | -| 02 | [Reward Hacking & Goodhart's Law](phases/18-ethics-safety-alignment/02-reward-hacking-goodhart/) | Learn | Python | -| 03 | [Direct Preference Optimization Family](phases/18-ethics-safety-alignment/03-direct-preference-optimization-family/) | Learn | Python | -| 04 | [Sycophancy as RLHF Amplification](phases/18-ethics-safety-alignment/04-sycophancy-rlhf-amplification/) | Learn | Python | -| 05 | [Constitutional AI & RLAIF](phases/18-ethics-safety-alignment/05-constitutional-ai-rlaif/) | Learn | Python | -| 06 | [Mesa-Optimization & Deceptive Alignment](phases/18-ethics-safety-alignment/06-mesa-optimization-deceptive-alignment/) | Learn | Python | -| 07 | [Sleeper Agents — Persistent Deception](phases/18-ethics-safety-alignment/07-sleeper-agents-persistent-deception/) | Learn | Python | -| 08 | [In-Context Scheming in Frontier Models](phases/18-ethics-safety-alignment/08-in-context-scheming-frontier-models/) | Learn | Python | -| 09 | [Alignment Faking](phases/18-ethics-safety-alignment/09-alignment-faking/) | Learn | Python | -| 10 | [AI Control — Safety Despite Subversion](phases/18-ethics-safety-alignment/10-ai-control-subversion/) | Learn | Python | -| 11 | [Scalable Oversight & Weak-to-Strong](phases/18-ethics-safety-alignment/11-scalable-oversight-weak-to-strong/) | Learn | Python | -| 12 | [Red-Teaming: PAIR & Automated Attacks](phases/18-ethics-safety-alignment/12-red-teaming-pair-automated-attacks/) | Build | Python | -| 13 | [Many-Shot Jailbreaking](phases/18-ethics-safety-alignment/13-many-shot-jailbreaking/) | Learn | Python | -| 14 | [ASCII Art & Visual Jailbreaks](phases/18-ethics-safety-alignment/14-ascii-art-visual-jailbreaks/) | Build | Python | -| 15 | [Indirect Prompt Injection](phases/18-ethics-safety-alignment/15-indirect-prompt-injection/) | Build | Python | -| 16 | [Red-Team Tooling: Garak, Llama Guard, PyRIT](phases/18-ethics-safety-alignment/16-red-team-tooling-garak-llamaguard-pyrit/) | Build | Python | -| 17 | [WMDP & Dual-Use Capability Evaluation](phases/18-ethics-safety-alignment/17-wmdp-dual-use-evaluation/) | Learn | Python | -| 18 | [Frontier Safety Frameworks — RSP, PF, FSF](phases/18-ethics-safety-alignment/18-frontier-safety-frameworks-rsp-pf-fsf/) | Learn | Python | -| 19 | [Model Welfare Research](phases/18-ethics-safety-alignment/19-model-welfare-research/) | Learn | Python | -| 20 | [Bias & Representational Harm](phases/18-ethics-safety-alignment/20-bias-representational-harm/) | Build | Python | -| 21 | [Fairness Criteria: Group, Individual, Counterfactual](phases/18-ethics-safety-alignment/21-fairness-criteria-group-individual-counterfactual/) | Learn | Python | -| 22 | [Differential Privacy for LLMs](phases/18-ethics-safety-alignment/22-differential-privacy-for-llms/) | Build | Python | -| 23 | [Watermarking: SynthID, Stable Signature, C2PA](phases/18-ethics-safety-alignment/23-watermarking-synthid-stable-signature-c2pa/) | Build | Python | -| 24 | [Regulatory Frameworks: EU, US, UK, Korea](phases/18-ethics-safety-alignment/24-regulatory-frameworks-eu-us-uk-korea/) | Learn | Python | -| 25 | [EchoLeak & CVEs for AI](phases/18-ethics-safety-alignment/25-echoleak-cves-for-ai/) | Learn | Python | -| 26 | [Model, System & Dataset Cards](phases/18-ethics-safety-alignment/26-model-system-dataset-cards/) | Build | Python | -| 27 | [Data Provenance & Training-Data Governance](phases/18-ethics-safety-alignment/27-data-provenance-training-governance/) | Learn | Python | -| 28 | [Alignment Research Ecosystem: MATS, Redwood, Apollo, METR](phases/18-ethics-safety-alignment/28-alignment-research-ecosystem/) | Learn | Python | -| 29 | [Moderation Systems: OpenAI, Perspective, Llama Guard](phases/18-ethics-safety-alignment/29-moderation-systems-openai-perspective-llamaguard/) | Build | Python | -| 30 | [Dual-Use Risk: Cyber, Bio, Chem, Nuclear](phases/18-ethics-safety-alignment/30-dual-use-risk-cyber-bio-chem-nuclear/) | Learn | Python | +| 01 | [指令遵循作为对齐信号](phases/18-ethics-safety-alignment/01-instruction-following-alignment-signal/) | 学习 | Python | +| 02 | [奖励黑客与古德哈特定律（Goodhart's Law）](phases/18-ethics-safety-alignment/02-reward-hacking-goodhart/) | 学习 | Python | +| 03 | [直接偏好优化（DPO）系列](phases/18-ethics-safety-alignment/03-direct-preference-optimization-family/) | 学习 | Python | +| 04 | [谄媚作为 RLHF 放大效应](phases/18-ethics-safety-alignment/04-sycophancy-rlhf-amplification/) | 学习 | Python | +| 05 | [宪法式 AI 与 RLAIF](phases/18-ethics-safety-alignment/05-constitutional-ai-rlaif/) | 学习 | Python | +| 06 | [Mesa 优化与欺骗性对齐（Mesa-Optimization）](phases/18-ethics-safety-alignment/06-mesa-optimization-deceptive-alignment/) | 学习 | Python | +| 07 | [休眠智能体——持久欺骗（Sleeper Agents）](phases/18-ethics-safety-alignment/07-sleeper-agents-persistent-deception/) | 学习 | Python | +| 08 | [前沿模型中的上下文阴谋（In-Context Scheming）](phases/18-ethics-safety-alignment/08-in-context-scheming-frontier-models/) | 学习 | Python | +| 09 | [对齐伪装（Alignment Faking）](phases/18-ethics-safety-alignment/09-alignment-faking/) | 学习 | Python | +| 10 | [AI 控制——面对颠覆仍保安全](phases/18-ethics-safety-alignment/10-ai-control-subversion/) | 学习 | Python | +| 11 | [可扩展监督与弱到强（Weak-to-Strong）](phases/18-ethics-safety-alignment/11-scalable-oversight-weak-to-strong/) | 学习 | Python | +| 12 | [红队测试：PAIR 与自动化攻击](phases/18-ethics-safety-alignment/12-red-teaming-pair-automated-attacks/) | 构建 | Python | +| 13 | [多轮越狱（Many-Shot Jailbreaking）](phases/18-ethics-safety-alignment/13-many-shot-jailbreaking/) | 学习 | Python | +| 14 | [ASCII 艺术与视觉越狱](phases/18-ethics-safety-alignment/14-ascii-art-visual-jailbreaks/) | 构建 | Python | +| 15 | [间接提示注入](phases/18-ethics-safety-alignment/15-indirect-prompt-injection/) | 构建 | Python | +| 16 | [红队工具：Garak、Llama Guard、PyRIT](phases/18-ethics-safety-alignment/16-red-team-tooling-garak-llamaguard-pyrit/) | 构建 | Python | +| 17 | [WMDP 与双重用途能力评估](phases/18-ethics-safety-alignment/17-wmdp-dual-use-evaluation/) | 学习 | Python | +| 18 | [前沿安全框架——RSP、PF、FSF](phases/18-ethics-safety-alignment/18-frontier-safety-frameworks-rsp-pf-fsf/) | 学习 | Python | +| 19 | [模型福祉研究](phases/18-ethics-safety-alignment/19-model-welfare-research/) | 学习 | Python | +| 20 | [偏见与表征伤害](phases/18-ethics-safety-alignment/20-bias-representational-harm/) | 构建 | Python | +| 21 | [公平性准则：群体、个体与反事实](phases/18-ethics-safety-alignment/21-fairness-criteria-group-individual-counterfactual/) | 学习 | Python | +| 22 | [面向 LLM 的差分隐私](phases/18-ethics-safety-alignment/22-differential-privacy-for-llms/) | 构建 | Python | +| 23 | [水印：SynthID、Stable Signature、C2PA](phases/18-ethics-safety-alignment/23-watermarking-synthid-stable-signature-c2pa/) | 构建 | Python | +| 24 | [监管框架：欧盟、美国、英国、韩国](phases/18-ethics-safety-alignment/24-regulatory-frameworks-eu-us-uk-korea/) | 学习 | Python | +| 25 | [EchoLeak 与 AI 相关 CVE](phases/18-ethics-safety-alignment/25-echoleak-cves-for-ai/) | 学习 | Python | +| 26 | [模型、系统与数据集卡片](phases/18-ethics-safety-alignment/26-model-system-dataset-cards/) | 构建 | Python | +| 27 | [数据溯源与训练数据治理](phases/18-ethics-safety-alignment/27-data-provenance-training-governance/) | 学习 | Python | +| 28 | [对齐研究生态：MATS、Redwood、Apollo、METR](phases/18-ethics-safety-alignment/28-alignment-research-ecosystem/) | 学习 | Python | +| 29 | [审核系统：OpenAI、Perspective、Llama Guard](phases/18-ethics-safety-alignment/29-moderation-systems-openai-perspective-llamaguard/) | 构建 | Python | +| 30 | [双重用途风险：网络、生物、化学、核能](phases/18-ethics-safety-alignment/30-dual-use-risk-cyber-bio-chem-nuclear/) | 学习 | Python |
-Phase 19 — Capstone Projects  85 lessons  17 end-to-end products + 9 deep-build tracks. 20-40 hours per project; 4-12 lessons per track. +第 19 阶段 — 毕业设计项目  85 lessons  17 个端到端产品 + 9 条深度构建轨道。每个项目 20–40 小时；每条轨道 4–12 节课。
-| # | Project | Combines | Lang | +| # | 项目 | 综合 | 语言 | |:---:|---------|----------|------| -| 01 | [Terminal-Native Coding Agent](phases/19-capstone-projects/01-terminal-native-coding-agent/) | P0 P5 P7 P10 P11 P13 P14 P15 P17 P18 | Python | -| 02 | [RAG over Codebase (Cross-Repo Semantic Search)](phases/19-capstone-projects/02-rag-over-codebase/) | P5 P7 P11 P13 P17 | Python | -| 03 | [Real-Time Voice Assistant (ASR → LLM → TTS)](phases/19-capstone-projects/03-realtime-voice-assistant/) | P6 P7 P11 P13 P14 P17 | Python | -| 04 | [Multimodal Document QA (Vision-First)](phases/19-capstone-projects/04-multimodal-document-qa/) | P4 P5 P7 P11 P12 P17 | Python | -| 05 | [Autonomous Research Agent (AI-Scientist Class)](phases/19-capstone-projects/05-autonomous-research-agent/) | P0 P2 P3 P7 P10 P14 P15 P16 P18 | Python | -| 06 | [DevOps Troubleshooting Agent for Kubernetes](phases/19-capstone-projects/06-devops-troubleshooting-agent/) | P11 P13 P14 P15 P17 P18 | Python | -| 07 | [End-to-End Fine-Tuning Pipeline](phases/19-capstone-projects/07-end-to-end-fine-tuning-pipeline/) | P2 P3 P7 P10 P11 P17 P18 | Python | -| 08 | [Production RAG Chatbot (Regulated Vertical)](phases/19-capstone-projects/08-production-rag-chatbot/) | P5 P7 P11 P12 P17 P18 | Python | -| 09 | [Code Migration Agent (Repo-Level Upgrade)](phases/19-capstone-projects/09-code-migration-agent/) | P5 P7 P11 P13 P14 P15 P17 | Python | -| 10 | [Multi-Agent Software Engineering Team](phases/19-capstone-projects/10-multi-agent-software-team/) | P11 P13 P14 P15 P16 P17 | Python | -| 11 | [LLM Observability & Eval Dashboard](phases/19-capstone-projects/11-llm-observability-dashboard/) | P11 P13 P17 P18 | Python | -| 12 | [Video Understanding Pipeline (Scene → QA)](phases/19-capstone-projects/12-video-understanding-pipeline/) | P4 P6 P7 P11 P12 P17 | Python | -| 13 | [MCP Server with Registry and Governance](phases/19-capstone-projects/13-mcp-server-with-registry/) | P11 P13 P14 P17 P18 | Python | -| 14 | [Speculative-Decoding Inference Server](phases/19-capstone-projects/14-speculative-decoding-server/) | P3 P7 P10 P17 | Python | -| 15 | [Constitutional Safety Harness + Red-Team Range](phases/19-capstone-projects/15-constitutional-safety-harness/) | P10 P11 P13 P14 P18 | Python | -| 16 | [GitHub Issue-to-PR Autonomous Agent](phases/19-capstone-projects/16-github-issue-to-pr-agent/) | P11 P13 P14 P15 P17 | Python | -| 17 | [Personal AI Tutor (Adaptive, Multimodal)](phases/19-capstone-projects/17-personal-ai-tutor/) | P5 P6 P11 P12 P14 P17 P18 | Python | +| 01 | [终端原生编码智能体](phases/19-capstone-projects/01-terminal-native-coding-agent/) | P0 P5 P7 P10 P11 P13 P14 P15 P17 P18 | Python | +| 02 | [代码库 RAG（跨仓库语义搜索）](phases/19-capstone-projects/02-rag-over-codebase/) | P5 P7 P11 P13 P17 | Python | +| 03 | [实时语音助手（ASR → LLM → TTS）](phases/19-capstone-projects/03-realtime-voice-assistant/) | P6 P7 P11 P13 P14 P17 | Python | +| 04 | [多模态文档问答（视觉优先）](phases/19-capstone-projects/04-multimodal-document-qa/) | P4 P5 P7 P11 P12 P17 | Python | +| 05 | [自主研究智能体（AI-Scientist 级别）](phases/19-capstone-projects/05-autonomous-research-agent/) | P0 P2 P3 P7 P10 P14 P15 P16 P18 | Python | +| 06 | [面向 Kubernetes 的 DevOps 排障智能体](phases/19-capstone-projects/06-devops-troubleshooting-agent/) | P11 P13 P14 P15 P17 P18 | Python | +| 07 | [端到端微调流水线](phases/19-capstone-projects/07-end-to-end-fine-tuning-pipeline/) | P2 P3 P7 P10 P11 P17 P18 | Python | +| 08 | [生产级 RAG 聊天机器人（受监管垂直领域）](phases/19-capstone-projects/08-production-rag-chatbot/) | P5 P7 P11 P12 P17 P18 | Python | +| 09 | [代码迁移智能体（仓库级升级）](phases/19-capstone-projects/09-code-migration-agent/) | P5 P7 P11 P13 P14 P15 P17 | Python | +| 10 | [多智能体软件工程团队](phases/19-capstone-projects/10-multi-agent-software-team/) | P11 P13 P14 P15 P16 P17 | Python | +| 11 | [LLM 可观测性与评估仪表盘](phases/19-capstone-projects/11-llm-observability-dashboard/) | P11 P13 P17 P18 | Python | +| 12 | [视频理解流水线（场景 → 问答）](phases/19-capstone-projects/12-video-understanding-pipeline/) | P4 P6 P7 P11 P12 P17 | Python | +| 13 | [带注册表与治理的 MCP 服务器](phases/19-capstone-projects/13-mcp-server-with-registry/) | P11 P13 P14 P17 P18 | Python | +| 14 | [推测解码推理服务器](phases/19-capstone-projects/14-speculative-decoding-server/) | P3 P7 P10 P17 | Python | +| 15 | [宪法式安全框架 + 红队靶场](phases/19-capstone-projects/15-constitutional-safety-harness/) | P10 P11 P13 P14 P18 | Python | +| 16 | [GitHub Issue 到 PR 自主智能体](phases/19-capstone-projects/16-github-issue-to-pr-agent/) | P11 P13 P14 P15 P17 | Python | +| 17 | [个人 AI 导师（自适应、多模态）](phases/19-capstone-projects/17-personal-ai-tutor/) | P5 P6 P11 P12 P14 P17 P18 | Python | -**Deep-build tracks** — multi-lesson series that build a complete subsystem from scratch. +**深度构建轨道** — 从零构建完整子系统的多节课系列。 -| # | Project | Combines | Lang | +| # | 项目 | 综合 | 语言 | |:---:|---------|----------|------| -| 20 | [Agent Harness Loop Contract](phases/19-capstone-projects/20-agent-harness-loop-contract/) | A. Agent harness | Python | -| 21 | [Tool Registry with Schema Validation](phases/19-capstone-projects/21-tool-registry-schema-validation/) | A. Agent harness | Python | -| 22 | [JSON-RPC 2.0 Over Newline-Delimited Stdio](phases/19-capstone-projects/22-jsonrpc-stdio-transport/) | A. Agent harness | Python | -| 23 | [Function Call Dispatcher](phases/19-capstone-projects/23-function-call-dispatcher/) | A. Agent harness | Python | -| 24 | [Plan-Execute Control Flow](phases/19-capstone-projects/24-plan-execute-control-flow/) | A. Agent harness | Python | -| 25 | [Verification Gates and Observation Budget](phases/19-capstone-projects/25-verification-gates-observation-budget/) | A. Agent harness | Python | -| 26 | [Sandbox Runner with Denylist and Path Jail](phases/19-capstone-projects/26-sandbox-runner-denylist/) | A. Agent harness | Python | -| 27 | [Eval Harness with Fixture Tasks](phases/19-capstone-projects/27-eval-harness-fixture-tasks/) | A. Agent harness | Python | -| 28 | [Observability with OTel GenAI Spans and Prometheus Metrics](phases/19-capstone-projects/28-observability-otel-traces/) | A. Agent harness | Python | -| 29 | [End-to-End Coding Agent on the Harness](phases/19-capstone-projects/29-end-to-end-coding-task-demo/) | A. Agent harness | Python | -| 30 | [BPE Tokenizer From Scratch](phases/19-capstone-projects/30-bpe-tokenizer-from-scratch/) | B. NLP LLM | Python | -| 31 | [Tokenized Dataset with Sliding Window](phases/19-capstone-projects/31-tokenized-dataset-sliding-window/) | B. NLP LLM | Python | -| 32 | [Token and Positional Embeddings](phases/19-capstone-projects/32-token-positional-embeddings/) | B. NLP LLM | Python | -| 33 | [Multi-Head Self-Attention](phases/19-capstone-projects/33-multihead-self-attention/) | B. NLP LLM | Python | -| 34 | [Transformer Block from Scratch](phases/19-capstone-projects/34-transformer-block/) | B. NLP LLM | Python | -| 35 | [GPT Model Assembly](phases/19-capstone-projects/35-gpt-model-assembly/) | B. NLP LLM | Python | -| 36 | [Training Loop and Evaluation](phases/19-capstone-projects/36-training-loop-eval/) | B. NLP LLM | Python | -| 37 | [Loading Pretrained Weights](phases/19-capstone-projects/37-loading-pretrained-weights/) | B. NLP LLM | Python | -| 38 | [Classifier Fine-Tuning by Head Swap](phases/19-capstone-projects/38-classifier-finetuning/) | B. NLP LLM | Python | -| 39 | [Instruction Tuning by Supervised Fine-Tuning](phases/19-capstone-projects/39-instruction-tuning-sft/) | B. NLP LLM | Python | -| 40 | [Direct Preference Optimization from Scratch](phases/19-capstone-projects/40-dpo-from-scratch/) | B. NLP LLM | Python | -| 41 | [Full Evaluation Pipeline](phases/19-capstone-projects/41-eval-pipeline/) | B. NLP LLM | Python | -| 42 | [Large Corpus Downloader](phases/19-capstone-projects/42-large-corpus-downloader/) | C. Train end-to-end | Python | -| 43 | [HDF5 Tokenized Corpus](phases/19-capstone-projects/43-hdf5-tokenized-corpus/) | C. Train end-to-end | Python | -| 44 | [Cosine LR with Linear Warmup](phases/19-capstone-projects/44-cosine-lr-warmup/) | C. Train end-to-end | Python | -| 45 | [Gradient Clipping and Mixed Precision](phases/19-capstone-projects/45-gradient-clipping-amp/) | C. Train end-to-end | Python | -| 46 | [Gradient Accumulation](phases/19-capstone-projects/46-gradient-accumulation/) | C. Train end-to-end | Python | -| 47 | [Checkpoint Save and Resume](phases/19-capstone-projects/47-checkpoint-save-resume/) | C. Train end-to-end | Python | -| 48 | [Distributed Data Parallel and FSDP from Scratch](phases/19-capstone-projects/48-distributed-fsdp-ddp/) | C. Train end-to-end | Python | -| 49 | [Language Model Evaluation Harness](phases/19-capstone-projects/49-lm-eval-harness/) | C. Train end-to-end | Python | -| 50 | [Hypothesis Generator](phases/19-capstone-projects/50-hypothesis-generator/) | D. Auto research | Python | -| 51 | [Literature Retrieval](phases/19-capstone-projects/51-literature-retrieval/) | D. Auto research | Python | -| 52 | [Experiment Runner](phases/19-capstone-projects/52-experiment-runner/) | D. Auto research | Python | -| 53 | [Result Evaluator](phases/19-capstone-projects/53-result-evaluator/) | D. Auto research | Python | -| 54 | [Paper Writer](phases/19-capstone-projects/54-paper-writer/) | D. Auto research | Python | -| 55 | [Critic Loop](phases/19-capstone-projects/55-critic-loop/) | D. Auto research | Python | -| 56 | [Iteration Scheduler](phases/19-capstone-projects/56-iteration-scheduler/) | D. Auto research | Python | -| 57 | [End-to-End Research Demo](phases/19-capstone-projects/57-end-to-end-research-demo/) | D. Auto research | Python | -| 58 | [Vision Encoder Patches](phases/19-capstone-projects/58-vision-encoder-patches/) | E. Multimodal VLM | Python | -| 59 | [Vision Transformer Encoder](phases/19-capstone-projects/59-vit-transformer/) | E. Multimodal VLM | Python | -| 60 | [Projection Layer for Modality Alignment](phases/19-capstone-projects/60-projection-layer-modality-align/) | E. Multimodal VLM | Python | -| 61 | [Cross-Attention Fusion](phases/19-capstone-projects/61-cross-attention-fusion/) | E. Multimodal VLM | Python | -| 62 | [Vision-Language Pretraining](phases/19-capstone-projects/62-vision-language-pretraining/) | E. Multimodal VLM | Python | -| 63 | [Multimodal Evaluation](phases/19-capstone-projects/63-multimodal-eval/) | E. Multimodal VLM | Python | -| 64 | [Chunking Strategies, Compared](phases/19-capstone-projects/64-chunking-strategies-advanced/) | F. Advanced RAG | Python | -| 65 | [Hybrid Retrieval with BM25 and Dense Embeddings](phases/19-capstone-projects/65-hybrid-retrieval-bm25-dense/) | F. Advanced RAG | Python | -| 66 | [Cross-Encoder Reranker](phases/19-capstone-projects/66-reranker-cross-encoder/) | F. Advanced RAG | Python | -| 67 | [Query Rewriting: HyDE, Multi-Query, and Decomposition](phases/19-capstone-projects/67-query-rewriting-hyde/) | F. Advanced RAG | Python | -| 68 | [RAG Evaluation: Precision, Recall, MRR, nDCG, Faithfulness, Answer Relevance](phases/19-capstone-projects/68-rag-eval-precision-recall/) | F. Advanced RAG | Python | -| 69 | [End-to-End RAG System](phases/19-capstone-projects/69-end-to-end-rag-system/) | F. Advanced RAG | Python | -| 70 | [Task Spec Format](phases/19-capstone-projects/70-task-spec-format/) | G. Eval framework | Python | -| 71 | [Classical Metrics](phases/19-capstone-projects/71-classical-metrics/) | G. Eval framework | Python | -| 72 | [Code Exec Metric](phases/19-capstone-projects/72-code-exec-metric/) | G. Eval framework | Python | -| 73 | [Perplexity and Calibration](phases/19-capstone-projects/73-perplexity-calibration/) | G. Eval framework | Python | -| 74 | [Leaderboard Aggregation](phases/19-capstone-projects/74-leaderboard-aggregation/) | G. Eval framework | Python | -| 75 | [End-to-End Eval Runner](phases/19-capstone-projects/75-end-to-end-eval-runner/) | G. Eval framework | Python | -| 76 | [Collective Ops From Scratch](phases/19-capstone-projects/76-collective-ops-from-scratch/) | H. Distributed train | Python | -| 77 | [Data Parallel DDP From Scratch](phases/19-capstone-projects/77-data-parallel-ddp/) | H. Distributed train | Python | -| 78 | [ZeRO Optimizer State Sharding](phases/19-capstone-projects/78-zero-parameter-sharding/) | H. Distributed train | Python | -| 79 | [Pipeline Parallel and Bubble Analysis](phases/19-capstone-projects/79-pipeline-parallel/) | H. Distributed train | Python | -| 80 | [Sharded Checkpoint and Atomic Resume](phases/19-capstone-projects/80-checkpoint-sharded-resume/) | H. Distributed train | Python | -| 81 | [End-to-End Distributed Training](phases/19-capstone-projects/81-end-to-end-distributed-train/) | H. Distributed train | Python | -| 82 | [Jailbreak Taxonomy](phases/19-capstone-projects/82-jailbreak-taxonomy/) | I. Safety harness | Python | -| 83 | [Prompt Injection Detector](phases/19-capstone-projects/83-prompt-injection-detector/) | I. Safety harness | Python | -| 84 | [Refusal Evaluation](phases/19-capstone-projects/84-refusal-evaluation/) | I. Safety harness | Python | -| 85 | [Content Classifier Integration](phases/19-capstone-projects/85-content-classifier-integration/) | I. Safety harness | Python | -| 86 | [Constitutional Rules Engine](phases/19-capstone-projects/86-constitutional-rules-engine/) | I. Safety harness | Python, YAML | -| 87 | [End-to-End Safety Gate](phases/19-capstone-projects/87-end-to-end-safety-gate/) | I. Safety harness | Python | +| 20 | [智能体框架循环契约](phases/19-capstone-projects/20-agent-harness-loop-contract/) | A. Agent harness | Python | +| 21 | [带模式校验的工具注册表](phases/19-capstone-projects/21-tool-registry-schema-validation/) | A. Agent harness | Python | +| 22 | [基于换行分隔 Stdio 的 JSON-RPC 2.0](phases/19-capstone-projects/22-jsonrpc-stdio-transport/) | A. Agent harness | Python | +| 23 | [函数调用分发器](phases/19-capstone-projects/23-function-call-dispatcher/) | A. Agent harness | Python | +| 24 | [计划-执行控制流](phases/19-capstone-projects/24-plan-execute-control-flow/) | A. Agent harness | Python | +| 25 | [验证关卡与观测预算](phases/19-capstone-projects/25-verification-gates-observation-budget/) | A. Agent harness | Python | +| 26 | [带拒绝列表与路径沙箱的沙箱运行器](phases/19-capstone-projects/26-sandbox-runner-denylist/) | A. Agent harness | Python | +| 27 | [带固定任务夹具的评估框架](phases/19-capstone-projects/27-eval-harness-fixture-tasks/) | A. Agent harness | Python | +| 28 | [基于 OTel GenAI Span 与 Prometheus 指标的可观测性](phases/19-capstone-projects/28-observability-otel-traces/) | A. Agent harness | Python | +| 29 | [基于框架的端到端编码智能体](phases/19-capstone-projects/29-end-to-end-coding-task-demo/) | A. Agent harness | Python | +| 30 | [从零实现 BPE 分词器](phases/19-capstone-projects/30-bpe-tokenizer-from-scratch/) | B. NLP LLM | Python | +| 31 | [带滑动窗口的分词数据集](phases/19-capstone-projects/31-tokenized-dataset-sliding-window/) | B. NLP LLM | Python | +| 32 | [词元与位置嵌入](phases/19-capstone-projects/32-token-positional-embeddings/) | B. NLP LLM | Python | +| 32 | [多头自注意力](phases/19-capstone-projects/33-multihead-self-attention/) | B. NLP LLM | Python | +| 34 | [从零实现 Transformer 块](phases/19-capstone-projects/34-transformer-block/) | B. NLP LLM | Python | +| 35 | [GPT 模型组装](phases/19-capstone-projects/35-gpt-model-assembly/) | B. NLP LLM | Python | +| 36 | [训练循环与评估](phases/19-capstone-projects/36-training-loop-eval/) | B. NLP LLM | Python | +| 37 | [加载预训练权重](phases/19-capstone-projects/37-loading-pretrained-weights/) | B. NLP LLM | Python | +| 38 | [通过替换头部进行分类器微调](phases/19-capstone-projects/38-classifier-finetuning/) | B. NLP LLM | Python | +| 39 | [通过监督微调进行指令调优](phases/19-capstone-projects/39-instruction-tuning-sft/) | B. NLP LLM | Python | +| 40 | [从零实现直接偏好优化](phases/19-capstone-projects/40-dpo-from-scratch/) | B. NLP LLM | Python | +| 41 | [完整评估流水线](phases/19-capstone-projects/41-eval-pipeline/) | B. NLP LLM | Python | +| 42 | [大规模语料下载器](phases/19-capstone-projects/42-large-corpus-downloader/) | C. Train end-to-end | Python | +| 43 | [HDF5 分词语料库](phases/19-capstone-projects/43-hdf5-tokenized-corpus/) | C. Train end-to-end | Python | +| 44 | [带线性预热的余弦学习率](phases/19-capstone-projects/44-cosine-lr-warmup/) | C. Train end-to-end | Python | +| 45 | [梯度裁剪与混合精度](phases/19-capstone-projects/45-gradient-clipping-amp/) | C. Train end-to-end | Python | +| 46 | [梯度累积](phases/19-capstone-projects/46-gradient-accumulation/) | C. Train end-to-end | Python | +| 47 | [检查点保存与恢复](phases/19-capstone-projects/47-checkpoint-save-resume/) | C. Train end-to-end | Python | +| 48 | [从零实现分布式数据并行与 FSDP](phases/19-capstone-projects/48-distributed-fsdp-ddp/) | C. Train end-to-end | Python | +| 49 | [语言模型评估框架](phases/19-capstone-projects/49-lm-eval-harness/) | C. Train end-to-end | Python | +| 50 | [假设生成器](phases/19-capstone-projects/50-hypothesis-generator/) | D. Auto research | Python | +| 51 | [文献检索](phases/19-capstone-projects/51-literature-retrieval/) | D. Auto research | Python | +| 52 | [实验运行器](phases/19-capstone-projects/52-experiment-runner/) | D. Auto research | Python | +| 53 | [结果评估器](phases/19-capstone-projects/53-result-evaluator/) | D. Auto research | Python | +| 54 | [论文撰写器](phases/19-capstone-projects/54-paper-writer/) | D. Auto research | Python | +| 55 | [批评循环](phases/19-capstone-projects/55-critic-loop/) | D. Auto research | Python | +| 56 | [迭代调度器](phases/19-capstone-projects/56-iteration-scheduler/) | D. Auto research | Python | +| 57 | [端到端研究演示](phases/19-capstone-projects/57-end-to-end-research-demo/) | D. Auto research | Python | +| 58 | [视觉编码器补丁](phases/19-capstone-projects/58-vision-encoder-patches/) | E. Multimodal VLM | Python | +| 59 | [视觉 Transformer 编码器](phases/19-capstone-projects/59-vit-transformer/) | E. Multimodal VLM | Python | +| 60 | [用于模态对齐的投影层](phases/19-capstone-projects/60-projection-layer-modality-align/) | E. Multimodal VLM | Python | +| 61 | [交叉注意力融合](phases/19-capstone-projects/61-cross-attention-fusion/) | E. Multimodal VLM | Python | +| 62 | [视觉-语言预训练](phases/19-capstone-projects/62-vision-language-pretraining/) | E. Multimodal VLM | Python | +| 63 | [多模态评估](phases/19-capstone-projects/63-multimodal-eval/) | E. Multimodal VLM | Python | +| 64 | [分块策略对比](phases/19-capstone-projects/64-chunking-strategies-advanced/) | F. Advanced RAG | Python | +| 65 | [BM25 与稠密嵌入的混合检索](phases/19-capstone-projects/65-hybrid-retrieval-bm25-dense/) | F. Advanced RAG | Python | +| 66 | [交叉编码器重排序器](phases/19-capstone-projects/66-reranker-cross-encoder/) | F. Advanced RAG | Python | +| 67 | [查询改写：HyDE、多查询与分解](phases/19-capstone-projects/67-query-rewriting-hyde/) | F. Advanced RAG | Python | +| 68 | [RAG 评估：Precision、Recall、MRR、nDCG、Faithfulness、Answer Relevance](phases/19-capstone-projects/68-rag-eval-precision-recall/) | F. Advanced RAG | Python | +| 69 | [端到端 RAG 系统](phases/19-capstone-projects/69-end-to-end-rag-system/) | F. Advanced RAG | Python | +| 70 | [任务规格格式](phases/19-capstone-projects/70-task-spec-format/) | G. Eval framework | Python | +| 71 | [经典指标](phases/19-capstone-projects/71-classical-metrics/) | G. Eval framework | Python | +| 72 | [代码执行指标](phases/19-capstone-projects/72-code-exec-metric/) | G. Eval framework | Python | +| 73 | [困惑度与校准](phases/19-capstone-projects/73-perplexity-calibration/) | G. Eval framework | Python | +| 74 | [排行榜聚合](phases/19-capstone-projects/74-leaderboard-aggregation/) | G. Eval framework | Python | +| 75 | [端到端评估运行器](phases/19-capstone-projects/75-end-to-end-eval-runner/) | G. Eval framework | Python | +| 76 | [从零实现集合通信算子](phases/19-capstone-projects/76-collective-ops-from-scratch/) | H. Distributed train | Python | +| 77 | [从零实现数据并行 DDP](phases/19-capstone-projects/77-data-parallel-ddp/) | H. Distributed train | Python | +| 78 | [ZeRO 优化器状态分片](phases/19-capstone-projects/78-zero-parameter-sharding/) | H. Distributed train | Python | +| 79 | [流水线并行与气泡分析](phases/19-capstone-projects/79-pipeline-parallel/) | H. Distributed train | Python | +| 80 | [分片检查点与原子恢复](phases/19-capstone-projects/80-checkpoint-sharded-resume/) | H. Distributed train | Python | +| 81 | [端到端分布式训练](phases/19-capstone-projects/81-end-to-end-distributed-train/) | H. Distributed train | Python | +| 82 | [越狱分类体系](phases/19-capstone-projects/82-jailbreak-taxonomy/) | I. Safety harness | Python | +| 83 | [提示注入检测器](phases/19-capstone-projects/83-prompt-injection-detector/) | I. Safety harness | Python | +| 84 | [拒答评估](phases/19-capstone-projects/84-refusal-evaluation/) | I. Safety harness | Python | +| 85 | [内容分类器集成](phases/19-capstone-projects/85-content-classifier-integration/) | I. Safety harness | Python | +| 86 | [宪法规则引擎](phases/19-capstone-projects/86-constitutional-rules-engine/) | I. Safety harness | Python, YAML | +| 87 | [端到端安全关卡](phases/19-capstone-projects/87-end-to-end-safety-gate/) | I. Safety harness | Python |
@@ -936,9 +923,9 @@ Each Phase 14 workbench lesson (31-42) ships a `mission.md` briefing the agent b ░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒ ``` -## The toolkit +## 工具包 -Every lesson produces a reusable artifact. By the end you have: +每节课都会产出一个可复用的制品（artifact）。学完全部内容后，你将拥有： ``` outputs/ @@ -946,16 +933,16 @@ outputs/ └── skills/ SKILL.md files for AI coding agents ``` -Install them with `npx skills add`. Plug them into Claude, Cursor, Codex, -OpenClaw, Hermes, or any agent that reads a SKILL.md / AGENTS.md directory. -Real tools, not homework. +使用 `npx skills add` 安装它们。接入 Claude、Cursor、Codex、 +OpenClaw、Hermes，或任何会读取 SKILL.md / AGENTS.md 目录的智能体（agent）。 +真工具，不是作业。 -### Install every course skill into your agent +### 将课程中的全部 skill 安装到你的智能体 -The repo ships 388 skills and 99 prompts under `phases/**/outputs/`. +本仓库在 `phases/**/outputs/` 下提供 388 个 skill 和 99 个 prompt。 -**Recommended: install via [skills.sh](https://skills.sh).** No clone, no Python, -detects your agent's skills directory automatically: +**推荐：通过 [skills.sh](https://skills.sh).** 安装。** 无需克隆、无需 Python， +会自动检测你智能体的 skills 目录： ```bash npx skills add rohitg00/ai-engineering-from-scratch # every skill @@ -963,13 +950,13 @@ npx skills add rohitg00/ai-engineering-from-scratch --skill agent-loop # one npx skills add rohitg00/ai-engineering-from-scratch --phase 14 # one phase ``` -`skills` writes to whichever directory your agent picks up: `.claude/skills/`, -`.cursor/skills/`, `.codex/skills/`, OpenClaw's skills folder, Hermes's bundle -path, or any SKILL.md-aware tool. One command, every agent. +`skills` 会写入你的智能体实际读取的目录：`.claude/skills/`、 +`.cursor/skills/`、`.codex/skills/`、OpenClaw 的 skills 文件夹、Hermes 的 bundle +路径，或任何支持 SKILL.md 的工具。一条命令，适配所有智能体。 -**Advanced: offline / custom layout via `scripts/install_skills.py`.** Requires -cloning the repo. Useful when you need tag filters, dry-runs, or a non-default -layout: +**进阶：通过 `scripts/install_skills.py` 离线安装 / 自定义布局。** 需要 +克隆仓库。适用于需要标签过滤、dry-run 或非默认 +布局的场景： ```bash python3 scripts/install_skills.py # every skill, default --layout skills (nested) @@ -982,26 +969,25 @@ python3 scripts/install_skills.py --dry-run # pre python3 scripts/install_skills.py --force # overwrite existing files ``` -`` is the skills directory for your agent (examples: -`~/.claude/skills/`, `~/.cursor/skills/`, `~/.config/openclaw/skills/`, -`.skills/`, or any path your agent reads). +`` 是你的智能体使用的 skills 目录（示例： +`~/.claude/skills/`、`~/.cursor/skills/`、`~/.config/openclaw/skills/`、 +`.skills/`，或你的智能体读取的任意路径）。 -By default the script refuses to overwrite an existing destination and exits -with code 1 after listing every colliding path. Use `--dry-run` to preview -collisions or `--force` to overwrite. Every non-dry-run run writes a -`manifest.json` in the target with the full inventory grouped by type and -phase. Pick the layout your agent reads: +默认情况下，脚本不会覆盖已有目标目录，会在列出所有冲突路径后以退出码 1 结束。使用 `--dry-run` 预览 +冲突，或使用 `--force` 覆盖。每次非 dry-run 运行都会在目标目录写入 +`manifest.json`，其中包含按类型和 +阶段分组的完整清单。选择你的智能体读取的布局： -| `--layout` | Path written | +| `--layout` | 写入路径 | |---|---| -| `skills` | `//SKILL.md` (nested convention, supported by Claude / Cursor / Codex / OpenClaw / Hermes) | +| `skills` | `//SKILL.md`（嵌套约定，Claude / Cursor / Codex / OpenClaw / Hermes 均支持） | | `by-phase` | `/phase-NN/.md` | | `flat` | `/.md` | -### Drop the agent workbench into your own repo +### 将智能体工作台放入你自己的仓库 -The Phase 14 capstone ships a reusable Agent Workbench pack (AGENTS.md, schemas, -init / verify / handoff scripts). Scaffold it into any repo with: +Phase 14 毕业项目提供一个可复用的 Agent Workbench 包（AGENTS.md、schemas、 +init / verify / handoff 脚本）。可用以下命令将其脚手架到任意仓库： ```bash python3 scripts/scaffold_workbench.py path/to/your-repo # full pack + seeds @@ -1010,16 +996,16 @@ python3 scripts/scaffold_workbench.py path/to/your-repo --dry-run # preview onl python3 scripts/scaffold_workbench.py path/to/your-repo --force # overwrite ``` -You get the seven workbench surfaces wired up, a starter `task_board.json`, -and a fresh `agent_state.json` at `schema_version: 1`. From there: edit the -task, edit `AGENTS.md`, run `scripts/init_agent.py`, hand the contract to -your agent. The pack source lives at -`phases/14-agent-engineering/42-agent-workbench-capstone/outputs/agent-workbench-pack/`. +你会得到已接好的七个工作台界面、一个入门 `task_board.json`， +以及在 `schema_version: 1` 处的新建 `agent_state.json`。接下来：编辑 +任务、编辑 `AGENTS.md`、运行 `scripts/init_agent.py`，将合约交给 +你的智能体。包源码位于 +`phases/14-agent-engineering/42-agent-workbench-capstone/outputs/agent-workbench-pack/`。 -### Browse the entire course as JSON +### 以 JSON 浏览整门课程 -`scripts/build_catalog.py` walks every phase, every lesson, every artifact on -disk and writes `catalog.json` at the repo root. One file, every course truth. +`scripts/build_catalog.py` 会遍历每个阶段、每节课、磁盘上的每个制品， +并在仓库根目录写入 `catalog.json`。一个文件，涵盖课程的全部事实。 ```bash python3 scripts/build_catalog.py # writes /catalog.json @@ -1027,23 +1013,22 @@ python3 scripts/build_catalog.py --stdout # to stdout, do not touch repo python3 scripts/build_catalog.py --out path/to/file.json ``` -The catalog is filesystem-derived, not README-derived, so counts always match -what is actually on disk. Use it for site builds, downstream tooling, or to -verify the README counts have not drifted. Schema is documented at the top of -the script. +该目录由文件系统派生，而非 README 派生，因此计数始终与 +磁盘上的实际内容一致。可用于站点构建、下游工具链，或 +验证 README 中的计数是否发生漂移。Schema 记录在该 +脚本顶部。 -A GitHub Action (`.github/workflows/curriculum.yml`) rebuilds `catalog.json` -on every PR and fails the build if the committed file is stale. After editing -any lesson, run `python3 scripts/build_catalog.py` and commit the result, or -CI will reject the PR. The same workflow runs `audit_lessons.py` in -warn-only mode (so existing drift does not block contributors). +GitHub Action（`.github/workflows/curriculum.yml`）会在每次 PR 时重建 `catalog.json`， +若已提交文件已过期则构建失败。编辑 +任意课程后，请运行 `python3 scripts/build_catalog.py` 并提交结果，否则 +CI 会拒绝该 PR。同一工作流会以仅警告模式运行 `audit_lessons.py`（ +因此既有漂移不会阻塞贡献者）。 -### Smoke-check every lesson's Python code +### 对每节课的 Python 代码做冒烟检查 -`scripts/lesson_run.py` byte-compiles every `.py` file under each lesson's -`code/` directory. Default mode is syntax-check only — no execution, no API -keys, no heavy ML deps required. Catches the regressions contributors -introduce most often (bad indentation, broken f-strings, stray edits). +`scripts/lesson_run.py` 会对每节课 `code/` 目录下所有 `.py` 文件进行字节码编译（byte-compile）。默认模式仅做语法检查——不执行、不需要 API +密钥、不需要重型 ML 依赖。可捕获贡献者 +最常引入的回归（错误缩进、损坏的 f-string、随意编辑）。 ```bash python3 scripts/lesson_run.py # syntax-check the whole curriculum @@ -1053,48 +1038,48 @@ python3 scripts/lesson_run.py --strict # exit 1 if any lesson fails python3 scripts/lesson_run.py --execute # actually run, 10s timeout per lesson ``` -`--execute` runs each lesson's `code/main.py` (or the first `.py` file) with a -10-second timeout. Lessons whose entry file starts with a `# requires: pkg1, -pkg2` comment listing non-stdlib deps are skipped with reason `needs `. -The script is opt-in and not wired into CI. +`--execute` 会以 10 秒超时运行每节课的 `code/main.py`（或第一个 `.py` 文件）。入口文件以 `# requires: pkg1, +pkg2` comment listing non-stdlib deps are skipped with reason `needs ` 开头的课程 +需要相应依赖。 +该脚本为可选启用，未接入 CI。 -Stdlib only, Python 3.10+. Set `LINK_CHECK_SKIP=domain1,domain2` to override -the default skip-list (`twitter.com`, `x.com`, `linkedin.com`, -`instagram.com`, `medium.com` — domains that aggressively block automated -HEAD/GET). +仅使用标准库，Python 3.10+。设置 `LINK_CHECK_SKIP=domain1,domain2` 可覆盖 +默认跳过列表（`twitter.com`、`x.com`、`linkedin.com`、 +`instagram.com`、`medium.com`——会积极拦截自动化 +HEAD/GET 的域名）。 -## Where to start +## 从哪里开始 -| Background | Start at | Estimated time | +| 背景 | 从这里开始 | 预估时间 | |---|---|---| -| New to programming and AI | Phase 0 — Setup | ~306 hours | -| Know Python, new to ML | Phase 1 — Math Foundations | ~270 hours | -| Know ML, new to deep learning | Phase 3 — Deep Learning Core | ~200 hours | -| Know deep learning, want LLMs and agents | Phase 10 — LLMs from Scratch | ~100 hours | -| Senior engineer, only want agent engineering | Phase 14 — Agent Engineering | ~60 hours | +| 编程与 AI 新手 | Phase 0 — Setup | ~306 小时 | +| 会 Python，ML 新手 | Phase 1 — Math Foundations | ~270 小时 | +| 会 ML，深度学习新手 | Phase 3 — Deep Learning Core | ~200 小时 | +| 会深度学习，想学 LLM 与智能体 | Phase 10 — LLMs from Scratch | ~100 小时 | +| 资深工程师，只想学智能体工程 | Phase 14 — Agent Engineering | ~60 小时 | ``` ░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒ ``` -## Why this matters now +## 为什么现在很重要 - - + +
FIG_003 · A
THE INDUSTRY SIGNAL		FIG_003 · B
FOUNDATIONAL PAPERS COVERED		FIG_003 · A
行业信号		FIG_003 · B
涵盖的基础论文
-> *"The hottest new programming language is English."*
-> — **Andrej Karpathy** ([tweet](https://x.com/karpathy/status/1617979122625712128)) +> *"最热门的新编程语言是英语。"*
+> — **Andrej Karpathy**（[推文](https://x.com/karpathy/status/1617979122625712128)) -> *"Software engineering is being remade in front of our eyes."*
-> — **Boris Cherny**, creator of Claude Code +> *"软件工程正在我们眼前被重塑。"*
+> — **Boris Cherny**，Claude Code 的创建者 -> *"Models will keep getting better. The skill that compounds is **knowing what to build**."*
-> — Industry consensus, 2026 +> *"模型会不断变好。能持续复利的能力是**知道该构建什么**。"*
+> — 行业共识，2026 		@@ -1116,18 +1101,18 @@ HEAD/GET). ░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒ ``` -## Contributing +## 贡献 -| Goal | Read | +| 目标 | 阅读 | |---|---| -| Contribute a lesson or fix | [CONTRIBUTING.md](CONTRIBUTING.md) | -| Fork for your team or school | [FORKING.md](FORKING.md) | -| Lesson template | [LESSON_TEMPLATE.md](LESSON_TEMPLATE.md) | -| Track progress | [ROADMAP.md](ROADMAP.md) | -| Glossary | [glossary/terms.md](glossary/terms.md) | -| Code of conduct | [CODE_OF_CONDUCT.md](CODE_OF_CONDUCT.md) | +| 贡献课程或修复 | [CONTRIBUTING.md](CONTRIBUTING.md) | +| 为你的团队或学校 Fork | [FORKING.md](FORKING.md) | +| 课程模板 | [LESSON_TEMPLATE.md](LESSON_TEMPLATE.md) | +| 跟踪进度 | [ROADMAP.md](ROADMAP.md) | +| 术语表 | [glossary/terms.md](glossary/terms.md) | +| 行为准则 | [CODE_OF_CONDUCT.md](CODE_OF_CONDUCT.md) | -Before submitting a lesson, run the invariant check: +提交课程前，请运行不变性检查： ```bash python3 scripts/audit_lessons.py # full curriculum @@ -1135,21 +1120,18 @@ python3 scripts/audit_lessons.py --phase 14 # single phase python3 scripts/audit_lessons.py --json # CI-friendly output ``` -Exit code is non-zero when any rule fails. Rules (L001–L010) validate directory -shape, `docs/en.md` presence + H1, `code/` non-emptiness, `quiz.json` schema -(rejects the legacy `q/choices/answer` keys that caused issue #102), and -relative links inside lesson docs. +当任意规则失败时，退出码为非零。规则（L001–L010）会校验目录结构、`docs/en.md` 是否存在及 H1、`code/` 非空、`quiz.json` 的模式（会拒绝曾导致 issue #102 的旧版 `q/choices/answer` 键），以及课程文档内的相对链接。 ``` ░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒ ``` -## Sponsor the work +## 赞助本项目 -Free, MIT-licensed, 503 lessons. The curriculum is maintained on sponsorship alone. Cash only. +免费、MIT 许可、503 门课程。本课程体系仅靠赞助维持。仅接受现金赞助。 -**Reach (verified 2026-05-14):** 55,593 monthly visitors · 90,709 page views · 7.5K stars · -Twitter/X is the #1 acquisition channel. +**影响力（2026-05-14 核实）：** 每月 55,593 名访客 · 90,709 次页面浏览 · 7.5K stars · +Twitter/X 是首要获客渠道。

@@ -1157,24 +1139,24 @@ Twitter/X is the #1 acquisition channel. Vercel OSS Program -**Current sponsors:** [CodeRabbit](https://coderabbit.link/rohit-ghumare) · [iii](https://iii.dev?utm_source=ai-engineering-from-scratch&utm_medium=readme&utm_campaign=sponsor) +**当前赞助商：** [CodeRabbit](https://coderabbit.link/rohit-ghumare) · [iii](https://iii.dev?utm_source=ai-engineering-from-scratch&utm_medium=readme&utm_campaign=sponsor) -| Tier | $/mo | What you get | +| 档位 | $/月 | 你将获得 | |------|------|---| -| Backer | $25 | Name in BACKERS.md | -| Bronze | $250 | Text-only row in README sponsor block + launch-day tweet | -| Silver | $750 | Small logo in README + listed as one supported provider in API lessons | -| Gold | $2,000 | Medium logo in README + sponsor page + quarterly X / LinkedIn co-feature | -| Platinum | $5,000 | Hero logo above the fold + one dedicated integration lesson, max 1 partner | +| Backer | $25 | 姓名列入 BACKERS.md | +| Bronze | $250 | README 赞助区块中的纯文本行 + 发布日当天推文 | +| Silver | $750 | README 中的小尺寸 Logo + 在 API 课程中列为受支持的提供商之一 | +| Gold | $2,000 | README 中的中等尺寸 Logo + 赞助页面 + 每季度在 X / LinkedIn 联合推广 | +| Platinum | $5,000 | 首屏 Hero Logo + 一门专属集成课程，最多 1 家合作伙伴 | -Full rate card, hard rules, pricing anchors, and reach data: [SPONSORS.md](SPONSORS.md). -Sign up via [GitHub Sponsors](https://github.com/sponsors/rohitg00). +完整价目表、硬性规则、定价参考及影响力数据：请参阅 [SPONSORS.md](SPONSORS.md)。 +通过 [GitHub Sponsors](https://github.com/sponsors/rohitg00). 注册赞助。 ``` ░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒ ``` -## Star history +## Star 历史 @@ -1183,17 +1165,16 @@ Sign up via [GitHub Sponsors](https://github.com/sponsors/rohitg00). -If this manual helped you, star the repo. It keeps the project alive. +如果本手册对你有帮助，请为仓库点 Star。这能让项目持续存续。 -## License +## 许可证 -MIT. Use it however you want — fork it, teach it, sell it, ship it. Attribution appreciated, -not required. +MIT。你可以随意使用——Fork、授课、销售、交付均可。署名感谢，但不强制。 -Maintained by [Rohit Ghumare](https://github.com/rohitg00) and the community. +由 [Rohit Ghumare](https://github.com/rohitg00) 及社区维护。 @ghumare64  ·  aiengineeringfromscratch.com  ·  - Report / Suggest + 报告问题 / 提出建议