能力标签

🔌 MCP 🤖 Agent 🔄 工作流 👁 OCR 🌐 翻译 🐳 Docker 💻 CLI 🧬 Embedding 📚 RAG 🖼 视觉

🔌

MCP工具

AI工程从零到精通

基于 Python · 让 AI 助手直接操作你的系统与工具

英文名：ai-engineering-from-scratch-zh

⭐ 486 Stars 🍴 78 Forks 💻 Python 📄 MIT 🏷 AI 8.5分

8.5AI 综合评分

aiai-agentsai-engineeringpythonchinese

⬇ 下载源码 ZIP ⚙️ 配置说明 📺 TG 频道

✦ AI Skill Hub 推荐

AI工程从零到精通是 AI Skill Hub 本期精选MCP工具之一。综合评分 8.5 分，整体质量较高。我们强烈推荐将其纳入你的 AI 工具库，帮助提升工作效率。

📚 深度解析

AI工程从零到精通是一款基于 MCP（Model Context Protocol）标准协议的 AI 工具扩展。MCP 协议由 Anthropic 开发并开源，旨在建立 AI 模型与外部工具之间的标准化通信接口，目前已被 Claude Desktop、Claude Code、Cursor 等主流 AI 工具采纳。

通过安装 AI工程从零到精通，你的 AI 助手将获得额外的工具调用能力，可以用自然语言直接操控该工具的功能，无需学习复杂的命令行语法。MCP 工具的核心价值在于"一次配置，永久增强"——配置完成后，每次与 AI 对话时都可以无缝调用这些工具。

在技术实现上，MCP 工具通过标准的 JSON-RPC 协议与 AI 客户端通信，工具的功能以"工具列表"的形式暴露给 AI 模型，AI 可以按需调用。AI工程从零到精通提供了结构化的工具调用接口，使 AI 模型能够精确地理解和使用每个功能点，显著降低 AI 在工具使用上的错误率。

与传统的 API 集成相比，MCP 工具的优势在于无需编写代码——用户只需在配置文件中添加几行 JSON，即可让 AI 获得全新能力。AI Skill Hub 将 AI工程从零到精通评为 AI 评分 8.5 分，属于同类工具中的优质选择。

📋 工具概览

AI工程从零到精通是一款遵循 MCP（Model Context Protocol）标准协议的 AI 工具扩展。通过 MCP 协议，它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务，实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用，都可以通过自然语言在 AI 对话中直接触发，极大提升生产效率。

GitHub Stars

⭐ 486

开发语言

Python

支持平台

Windows / macOS / Linux

维护状态

轻量级项目，按需更新

开源协议

MIT

AI 综合评分

8.5 分

工具类型

MCP工具

Forks

📖 中文文档

以下内容由 AI Skill Hub 根据项目信息自动整理，如需查看完整原始文档请访问底部「原始来源」。

📌 核心特色

通过标准 MCP 协议与 Claude、Cursor 等主流 AI 客户端深度集成
提供结构化工具调用接口，显著降低 AI 集成复杂度
支持 Claude Desktop 和 Claude Code 无缝接入，开箱即用
可与其他 MCP 工具组合叠加，构建完整 AI 工作站
轻量无侵入设计，不影响现有系统架构

🎯 主要使用场景

在 Claude Desktop 对话中直接调用本地工具，实现 AI 与系统的深度联动
通过自然语言驱动复杂的多步骤自动化任务，代替繁琐手动操作
将多个 MCP 工具组合使用，构建个人专属 AI 工作站

以下安装命令基于项目开发语言和类型自动生成，实际以官方 README 为准。

安装命令

# 方式一：通过 Claude Code CLI 一键安装
claude skill install https://github.com/fancyboi999/ai-engineering-from-scratch-zh

# 方式二：手动配置 claude_desktop_config.json
{
  "mcpServers": {
    "ai-------": {
      "command": "npx",
      "args": ["-y", "ai-engineering-from-scratch-zh"]
    }
  }
}

# 配置文件位置
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%/Claude/claude_desktop_config.json

📋 安装步骤说明

确认已安装 Node.js（v18 或以上版本）
打开 Claude Desktop 或 Claude Code 的 MCP 配置文件
按「交给 Agent 安装 → Claude Desktop」标签中的 JSON 配置填入 mcpServers 字段
保存配置文件并重启 Claude 客户端
重启后，在对话中即可使用本工具

以下用法示例由 AI Skill Hub 整理，涵盖最常见的使用场景。

常用命令 / 代码示例

# 安装后在 Claude 对话中直接使用
# 示例：
用户: 请帮我用 AI工程从零到精通 执行以下任务...
Claude: [自动调用 AI工程从零到精通 MCP 工具处理请求]

# 查看可用工具列表
# 在 Claude 中输入："列出所有可用的 MCP 工具"

以下配置示例基于典型使用场景生成，具体参数请参照官方文档调整。

配置示例

// claude_desktop_config.json 配置示例
{
  "mcpServers": {
    "ai_______": {
      "command": "npx",
      "args": ["-y", "ai-engineering-from-scratch-zh"],
      "env": {
        // "API_KEY": "your-api-key-here"
      }
    }
  }
}

// 保存后重启 Claude Desktop 生效

📑 README 深度解析真实文档完整度 32/100 含工作流图查看 GitHub 原文 →

以下内容由系统直接从 GitHub README 解析整理，保留代码块、表格与列表结构。

简介

从零开始，亲手实现每一个 AI 算法 503 节课 · 20 个阶段 · Python / TypeScript / Rust / Julia · 配套中文网站 <a href="https://aieng-zh.cn">aieng-zh.cn</a>

░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒░░░▒▒▒

84% 的学生已经在用 AI 工具，可只有 18% 觉得自己能在专业场景里用好它们。 这套课程要填的就是这道沟。 503 节课，20 个阶段，约 320 小时。Python、TypeScript、Rust、Julia。每节课都交付一件能复用的东西：一个提示词、一个技能、一个 agent、一个 MCP server。免费，开源，MIT。你不只是学 AI，你亲手把它造出来。从头到尾，全手写。

本项目是 AI Engineering from Scratch（作者 Rohit Ghumare，MIT 协议）的简体中文衍生版。衷心感谢原作者创作并开源了这套课程。

快速开始

三种入门方式。挑一个。

方式 A —— 阅读。 在 aieng-zh.cn 上打开任意一节已完成的课程，或展开目录里的某个阶段。无需配置，无需 clone。

方式 B —— clone 下来跑。

git clone https://github.com/fancyboi999/ai-engineering-from-scratch-zh.git
cd ai-engineering-from-scratch-zh
python phases/01-math-foundations/01-linear-algebra-intuition/code/vectors.py

**方式 C —— 测一测你的水平 (推荐)。** 聪明地跳级。在 Claude、Cursor、Codex、OpenClaw、Hermes，或任何装了本课程技能的 agent 里：

/find-your-level

十道题。把你的知识映射到一个起始阶段，生成一条带课时估算的个性化路径。每学完一个阶段：

```bash /check-understanding 3 # 测验你对阶段 3 的掌握 ls phases/03-deep-learning-core/05-loss-functions/outputs/

Phase 0: 配置与工具链 `12 lessons`

把环境准备好，迎接后面所有的内容。

#	Lesson	Type	Lang
01	[开发环境](phases/00-setup-and-tooling/01-dev-environment/)	Build	Python
02	[Git 与协作](phases/00-setup-and-tooling/02-git-and-collaboration/)	Learn	—
03	[GPU 配置与云端](phases/00-setup-and-tooling/03-gpu-setup-and-cloud/)	Build	Python
04	[API 与密钥](phases/00-setup-and-tooling/04-apis-and-keys/)	Build	Python
05	[Jupyter Notebook](phases/00-setup-and-tooling/05-jupyter-notebooks/)	Build	Python
06	[Python 环境管理](phases/00-setup-and-tooling/06-python-environments/)	Build	Shell
07	[面向 AI 的 Docker](phases/00-setup-and-tooling/07-docker-for-ai/)	Build	Docker
08	[编辑器配置](phases/00-setup-and-tooling/08-editor-setup/)	Build	—
09	[数据管理](phases/00-setup-and-tooling/09-data-management/)	Build	Python
10	[终端与 Shell](phases/00-setup-and-tooling/10-terminal-and-shell/)	Learn	—
11	[面向 AI 的 Linux](phases/00-setup-and-tooling/11-linux-for-ai/)	Learn	—
12	[调试与性能分析](phases/00-setup-and-tooling/12-debugging-and-profiling/)	Build	Python

<details id="phase-1"> <summary>Phase 1 — 数学基础  <code>22 lessons</code>  每个 AI 算法背后的直觉，用代码讲清楚。</summary>

#	Lesson	Type	Lang
01	[线性代数直觉](phases/01-math-foundations/01-linear-algebra-intuition/)	Learn	Python, Julia
02	[向量、矩阵与运算](phases/01-math-foundations/02-vectors-matrices-operations/)	Build	Python, Julia
03	[矩阵变换与特征值](phases/01-math-foundations/03-matrix-transformations/)	Build	Python, Julia
04	[机器学习里的微积分：导数与梯度](phases/01-math-foundations/04-calculus-for-ml/)	Learn	Python
05	[链式法则与自动微分](phases/01-math-foundations/05-chain-rule-and-autodiff/)	Build	Python
06	[概率与分布](phases/01-math-foundations/06-probability-and-distributions/)	Learn	Python
07	[贝叶斯定理与统计思维](phases/01-math-foundations/07-bayes-theorem/)	Build	Python
08	[优化：梯度下降家族](phases/01-math-foundations/08-optimization/)	Build	Python
09	[信息论：熵与 KL 散度](phases/01-math-foundations/09-information-theory/)	Learn	Python
10	[降维：PCA、t-SNE、UMAP](phases/01-math-foundations/10-dimensionality-reduction/)	Build	Python
11	[奇异值分解](phases/01-math-foundations/11-singular-value-decomposition/)	Build	Python, Julia
12	[张量运算](phases/01-math-foundations/12-tensor-operations/)	Build	Python
13	[数值稳定性](phases/01-math-foundations/13-numerical-stability/)	Build	Python
14	[范数与距离](phases/01-math-foundations/14-norms-and-distances/)	Build	Python
15	[机器学习里的统计学](phases/01-math-foundations/15-statistics-for-ml/)	Build	Python
16	[采样方法](phases/01-math-foundations/16-sampling-methods/)	Build	Python
17	[线性方程组](phases/01-math-foundations/17-linear-systems/)	Build	Python
18	[凸优化](phases/01-math-foundations/18-convex-optimization/)	Build	Python
19	[面向 AI 的复数](phases/01-math-foundations/19-complex-numbers/)	Learn	Python
20	[傅里叶变换](phases/01-math-foundations/20-fourier-transform/)	Build	Python
21	[机器学习里的图论](phases/01-math-foundations/21-graph-theory/)	Build	Python
22	[随机过程](phases/01-math-foundations/22-stochastic-processes/)	Learn	Python

</details>

<details id="phase-2"> <summary>Phase 2 — 机器学习基础  <code>18 lessons</code>  经典机器学习——至今仍是大多数生产 AI 的骨架。</summary>

#	Lesson	Type	Lang
01	[什么是机器学习](phases/02-ml-fundamentals/01-what-is-machine-learning/)	Learn	Python
02	[从零实现线性回归](phases/02-ml-fundamentals/02-linear-regression/)	Build	Python
03	[逻辑回归与分类](phases/02-ml-fundamentals/03-logistic-regression/)	Build	Python
04	[决策树与随机森林](phases/02-ml-fundamentals/04-decision-trees/)	Build	Python
05	[支持向量机](phases/02-ml-fundamentals/05-support-vector-machines/)	Build	Python
06	[KNN 与距离度量](phases/02-ml-fundamentals/06-knn-and-distances/)	Build	Python
07	[无监督学习：K-Means、DBSCAN](phases/02-ml-fundamentals/07-unsupervised-learning/)	Build	Python
08	[特征工程与特征选择](phases/02-ml-fundamentals/08-feature-engineering/)	Build	Python
09	[模型评估：指标与交叉验证](phases/02-ml-fundamentals/09-model-evaluation/)	Build	Python
10	[偏差、方差与学习曲线](phases/02-ml-fundamentals/10-bias-variance/)	Learn	Python
11	[集成方法：Boosting、Bagging、Stacking](phases/02-ml-fundamentals/11-ensemble-methods/)	Build	Python
12	[超参数调优](phases/02-ml-fundamentals/12-hyperparameter-tuning/)	Build	Python
13	[机器学习流水线与实验追踪](phases/02-ml-fundamentals/13-ml-pipelines/)	Build	Python
14	[朴素贝叶斯](phases/02-ml-fundamentals/14-naive-bayes/)	Build	Python
15	[时间序列基础](phases/02-ml-fundamentals/15-time-series/)	Build	Python
16	[异常检测](phases/02-ml-fundamentals/16-anomaly-detection/)	Build	Python
17	[处理不平衡数据](phases/02-ml-fundamentals/17-imbalanced-data/)	Build	Python
18	[特征选择](phases/02-ml-fundamentals/18-feature-selection/)	Build	Python

</details>

<details id="phase-3"> <summary>Phase 3 — 深度学习核心  <code>13 lessons</code>  从第一性原理出发的神经网络。先自己造一个，再碰框架。</summary>

#	Lesson	Type	Lang
01	[感知机：一切的起点](phases/03-deep-learning-core/01-the-perceptron/)	Build	Python
02	[多层网络与前向传播](phases/03-deep-learning-core/02-multi-layer-networks/)	Build	Python
03	[从零实现反向传播](phases/03-deep-learning-core/03-backpropagation/)	Build	Python
04	[激活函数：ReLU、Sigmoid、GELU 及其原因](phases/03-deep-learning-core/04-activation-functions/)	Build	Python
05	[损失函数：MSE、交叉熵、对比损失](phases/03-deep-learning-core/05-loss-functions/)	Build	Python
06	[优化器：SGD、Momentum、Adam、AdamW](phases/03-deep-learning-core/06-optimizers/)	Build	Python
07	[正则化：Dropout、权重衰减、BatchNorm](phases/03-deep-learning-core/07-regularization/)	Build	Python
08	[权重初始化与训练稳定性](phases/03-deep-learning-core/08-weight-initialization/)	Build	Python
09	[学习率调度与 Warmup](phases/03-deep-learning-core/09-learning-rate-schedules/)	Build	Python
10	[造一个你自己的迷你框架](phases/03-deep-learning-core/10-mini-framework/)	Build	Python
11	[PyTorch 入门](phases/03-deep-learning-core/11-intro-to-pytorch/)	Build	Python
12	[JAX 入门](phases/03-deep-learning-core/12-intro-to-jax/)	Build	Python
13	[调试神经网络](phases/03-deep-learning-core/13-debugging-neural-networks/)	Build	Python

</details>

<details id="phase-4"> <summary>Phase 4 — 计算机视觉  <code>28 lessons</code>  从像素到理解——图像、视频、3D、VLM 和世界模型。</summary>

#	Lesson	Type	Lang
01	[图像基础：像素、通道、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、NeRF](phases/04-computer-vision/13-3d-vision-nerf/)	Build	Python
14	[Vision 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	[构建一条完整的视觉流水线](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	[开放词表视觉——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	[Diffusion Transformer 与 Rectified Flow](phases/04-computer-vision/23-diffusion-transformers-rectified-flow/)	Build	Python
24	[SAM 3 与开放词表分割](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

</details>

<details id="phase-5"> <summary>Phase 5 — NLP：从基础到进阶  <code>29 lessons</code>  语言是通往智能的接口。</summary>

#	Lesson	Type	Lang
01	[文本处理：分词、词干提取、词形还原](phases/05-nlp-foundations-to-advanced/01-text-processing/)	Build	Python
02	[词袋、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——那次突破](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	[自然语言推理与文本蕴含](phases/05-nlp-foundations-to-advanced/21-nli-textual-entailment/)	Learn	Python
22	[嵌入模型深入剖析](phases/05-nlp-foundations-to-advanced/22-embedding-models-deep-dive/)	Learn	Python
23	[RAG 的分块策略](phases/05-nlp-foundations-to-advanced/23-chunking-strategies-rag/)	Build	Python
24	[指代消解](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

</details>

<details id="phase-6"> <summary>Phase 6 — 语音与音频  <code>17 lessons</code>  听见、听懂、开口说。</summary>

#	Lesson	Type	Lang
01	[音频基础：波形、采样、FFT](phases/06-speech-and-audio/01-audio-fundamentals)	Learn	Python
02	[频谱图、梅尔刻度与音频特征](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	[搭一条语音助手流水线](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	[语音活动检测与轮次切换](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	[语音防伪与音频水印](phases/06-speech-and-audio/16-anti-spoofing-audio-watermarking)	Build	Python
17	[音频评估——WER、MOS、MMAU、排行榜](phases/06-speech-and-audio/17-audio-evaluation-metrics)	Learn	Python

</details>

<details id="phase-7"> <summary>Phase 7 — Transformer 深入剖析  <code>16 lessons</code>  那个改变了一切的架构。</summary>

#	Lesson	Type	Lang
01	[为什么用 Transformer：RNN 的问题](phases/07-transformers-deep-dive/01-why-transformers/)	Learn	Python
02	[从零实现自注意力](phases/07-transformers-deep-dive/02-self-attention-from-scratch/)	Build	Python
03	[多头注意力](phases/07-transformers-deep-dive/03-multi-head-attention/)	Build	Python
04	[位置编码：正弦、RoPE、ALiBi](phases/07-transformers-deep-dive/04-positional-encoding/)	Build	Python
05	[完整的 Transformer：编码器 + 解码器](phases/07-transformers-deep-dive/05-full-transformer/)	Build	Python
06	[BERT——掩码语言建模](phases/07-transformers-deep-dive/06-bert-masked-language-modeling/)	Build	Python
07	[GPT——因果语言建模](phases/07-transformers-deep-dive/07-gpt-causal-language-modeling/)	Build	Python
08	[T5、BART——编码器-解码器模型](phases/07-transformers-deep-dive/08-t5-bart-encoder-decoder/)	Learn	Python
09	[Vision Transformer（ViT）](phases/07-transformers-deep-dive/09-vision-transformers/)	Build	Python
10	[音频 Transformer——Whisper 架构](phases/07-transformers-deep-dive/10-audio-transformers-whisper/)	Learn	Python
11	[专家混合（MoE）](phases/07-transformers-deep-dive/11-mixture-of-experts/)	Build	Python
12	[KV Cache、Flash Attention 与推理优化](phases/07-transformers-deep-dive/12-kv-cache-flash-attention/)	Build	Python
13	[缩放定律](phases/07-transformers-deep-dive/13-scaling-laws/)	Learn	Python
14	[从零构建一个 Transformer](phases/07-transformers-deep-dive/14-build-a-transformer-capstone/)	Build	Python
15	[Attention 变体——滑动窗口、稀疏、差分](phases/07-transformers-deep-dive/15-attention-variants/)	Build	Python
16	[投机解码——草稿、验证、重复](phases/07-transformers-deep-dive/16-speculative-decoding/)	Build	Python

</details>

<details id="phase-8"> <summary>Phase 8 — 生成式 AI  <code>15 lessons</code>  生成图像、视频、音频、3D，等等。</summary>

#	Lesson	Type	Lang
01	[生成模型：分类与历史](phases/08-generative-ai/01-generative-models-taxonomy-history/)	Learn	Python
02	[自编码器与 VAE](phases/08-generative-ai/02-autoencoders-vae/)	Build	Python
03	[GAN：生成器 vs 判别器](phases/08-generative-ai/03-gans-generator-discriminator/)	Build	Python
04	[条件 GAN 与 Pix2Pix](phases/08-generative-ai/04-conditional-gans-pix2pix/)	Build	Python
05	[StyleGAN](phases/08-generative-ai/05-stylegan/)	Build	Python
06	[扩散模型——从零实现 DDPM](phases/08-generative-ai/06-diffusion-ddpm-from-scratch/)	Build	Python
07	[潜在扩散与 Stable Diffusion](phases/08-generative-ai/07-latent-diffusion-stable-diffusion/)	Build	Python
08	[ControlNet、LoRA 与条件控制](phases/08-generative-ai/08-controlnet-lora-conditioning/)	Build	Python
09	[图像修复、扩展与编辑](phases/08-generative-ai/09-inpainting-outpainting-editing/)	Build	Python
10	[视频生成](phases/08-generative-ai/10-video-generation/)	Build	Python
11	[音频生成](phases/08-generative-ai/11-audio-generation/)	Build	Python
12	[3D 生成](phases/08-generative-ai/12-3d-generation/)	Build	Python
13	[Flow Matching 与 Rectified Flow](phases/08-generative-ai/13-flow-matching-rectified-flows/)	Build	Python
14	[评估：FID、CLIP Score](phases/08-generative-ai/14-evaluation-fid-clip-score/)	Build	Python
19	[视觉自回归建模（VAR）：下一尺度预测](phases/08-generative-ai/19-visual-autoregressive-var/)	Build	Python

</details>

<details id="phase-9"> <summary>Phase 9 — 强化学习  <code>12 lessons</code>  RLHF 和会玩游戏的 AI 的基石。</summary>

#	Lesson	Type	Lang
01	[MDP、状态、动作与奖励](phases/09-reinforcement-learning/01-mdps-states-actions-rewards/)	Learn	Python
02	[动态规划](phases/09-reinforcement-learning/02-dynamic-programming/)	Build	Python
03	[蒙特卡洛方法](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	[深度 Q 网络（DQN）](phases/09-reinforcement-learning/05-dqn/)	Build	Python
06	[策略梯度——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	[奖励建模与 RLHF](phases/09-reinforcement-learning/09-reward-modeling-rlhf/)	Build	Python
10	[多智能体强化学习](phases/09-reinforcement-learning/10-multi-agent-rl/)	Build	Python
11	[仿真到现实的迁移](phases/09-reinforcement-learning/11-sim-to-real-transfer/)	Build	Python
12	[游戏中的强化学习](phases/09-reinforcement-learning/12-rl-for-games/)	Build	Python

</details>

<details id="phase-10"> <summary>Phase 10 — 从零实现 LLM  <code>24 lessons</code>  构建、训练并真正理解大语言模型。</summary>

#	Lesson	Type	Lang
01	[分词器：BPE、WordPiece、SentencePiece](phases/10-llms-from-scratch/01-tokenizers/)	Build	Python, Rust
02	[从零实现一个分词器](phases/10-llms-from-scratch/02-building-a-tokenizer/)	Build	Python
03	[预训练的数据流水线](phases/10-llms-from-scratch/03-data-pipelines/)	Build	Python
04	[预训练一个迷你 GPT（124M）](phases/10-llms-from-scratch/04-pre-training-mini-gpt/)	Build	Python
05	[分布式训练、FSDP、DeepSpeed](phases/10-llms-from-scratch/05-scaling-distributed/)	Build	Python
06	[指令微调——SFT](phases/10-llms-from-scratch/06-instruction-tuning-sft/)	Build	Python
07	[RLHF——奖励模型 + PPO](phases/10-llms-from-scratch/07-rlhf/)	Build	Python
08	[DPO——直接偏好优化](phases/10-llms-from-scratch/08-dpo/)	Build	Python
09	[Constitutional AI 与自我改进](phases/10-llms-from-scratch/09-constitutional-ai-self-improvement/)	Build	Python
10	[评估——基准与 evals](phases/10-llms-from-scratch/10-evaluation/)	Build	Python
11	[量化：INT8、GPTQ、AWQ、GGUF](phases/10-llms-from-scratch/11-quantization/)	Build	Python
12	[推理优化](phases/10-llms-from-scratch/12-inference-optimization/)	Build	Python
13	[搭一条完整的 LLM 流水线](phases/10-llms-from-scratch/13-building-complete-llm-pipeline/)	Build	Python
14	[开源模型：架构逐一拆解](phases/10-llms-from-scratch/14-open-models-architecture-walkthroughs/)	Learn	Python
15	[投机解码与 EAGLE-3](phases/10-llms-from-scratch/15-speculative-decoding-eagle3/)	Build	Python
16	[差分注意力（V2）](phases/10-llms-from-scratch/16-differential-attention-v2/)	Build	Python
17	[原生稀疏注意力（DeepSeek NSA）](phases/10-llms-from-scratch/17-native-sparse-attention/)	Build	Python
18	[多 token 预测（MTP）](phases/10-llms-from-scratch/18-multi-token-prediction/)	Build	Python
19	[DualPipe 并行](phases/10-llms-from-scratch/19-dualpipe-parallelism/)	Learn	Python
20	[DeepSeek-V3 架构拆解](phases/10-llms-from-scratch/20-deepseek-v3-walkthrough/)	Learn	Python
21	[Jamba——SSM-Transformer 混合架构](phases/10-llms-from-scratch/21-jamba-hybrid-ssm-transformer/)	Learn	Python
22	[异步与 Hogwild! 推理](phases/10-llms-from-scratch/22-async-hogwild-inference/)	Build	Python
25	[推测解码与 EAGLE](phases/10-llms-from-scratch/25-speculative-decoding/)	Build	Python
34	[梯度检查点与激活重算](phases/10-llms-from-scratch/34-gradient-checkpointing/)	Build	Python

</details>

<details id="phase-11"> <summary>Phase 11 — LLM 工程  <code>17 lessons</code>  让 LLM 在生产环境里干活。</summary>

#	Lesson	Type	Lang
01	[提示工程：技巧与套路](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	[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](phases/11-llm-engineering/06-rag/)	Build	Python
07	[进阶 RAG：分块、重排](phases/11-llm-engineering/07-advanced-rag/)	Build	Python
08	[用 LoRA 与 QLoRA 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、限流与成本](phases/11-llm-engineering/11-caching-cost/)	Build	Python
12	[护栏与安全](phases/11-llm-engineering/12-guardrails/)	Build	Python
13	[构建一个生产级 LLM 应用](phases/11-llm-engineering/13-production-app/)	Build	Python
14	[模型上下文协议（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：面向 agent 的状态机](phases/11-llm-engineering/16-langgraph-state-machines/)	Build	Python
17	[agent 框架的取舍](phases/11-llm-engineering/17-agent-framework-tradeoffs/)	Learn	Python

</details>

<details id="phase-12"> <summary>Phase 12 — 多模态 AI  <code>25 lessons</code>  跨模态地看、听、读、推理——从 ViT 的图块到操作电脑的 agent。</summary>

#	Lesson	Type	Lang
01	[Vision Transformer 与图块-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	[开源权重 VLM 配方：真正要紧的是什么](phases/12-multimodal-ai/07-open-weight-vlm-recipes/)	Learn	Python
08	[LLaVA-OneVision：单图、多图、视频](phases/12-multimodal-ai/08-llava-onevision-single-multi-video/)	Build	Python
09	[Qwen-VL 家族与动态 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 早融合纯 token](phases/12-multimodal-ai/11-chameleon-early-fusion-tokens/)	Build	Python
12	[Emu3 用下一 token 预测做生成](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 离散扩散统一架构](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](phases/12-multimodal-ai/16-mio-any-to-any-streaming/)	Learn	Python
17	[视频语言时序定位](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](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 agent 与操作电脑（综合项目）](phases/12-multimodal-ai/25-multimodal-agents-computer-use/)	Build	Python

</details>

<details id="phase-13"> <summary>Phase 13 — 工具与协议  <code>23 lessons</code>  AI 与真实世界之间的接口。</summary>

#	Lesson	Type	Lang
01	[工具接口](phases/13-tools-and-protocols/01-the-tool-interface/)	Learn	Python
02	[函数调用深入剖析](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 Schema 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	[构建一个 MCP server](phases/13-tools-and-protocols/07-building-an-mcp-server/)	Build	Python
08	[构建一个 MCP client](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 Sampling](phases/13-tools-and-protocols/11-mcp-sampling/)	Build	Python
12	[MCP Roots 与 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 Apps](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	[生产环境的 MCP 认证——iii 上的 DCR + JWKS](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 路由层](phases/13-tools-and-protocols/21-llm-routing-layer/)	Learn	Python
22	[Skills 与 Agent SDK](phases/13-tools-and-protocols/22-skills-and-agent-sdks/)	Learn	Python
23	[综合项目——工具生态](phases/13-tools-and-protocols/23-capstone-tool-ecosystem/)	Build	Python

</details>

<details id="phase-14"> <summary>Phase 14 — Agent 工程  <code>42 lessons</code>  从第一性原理构建 agent——循环、记忆、规划、框架、基准、生产、工作台。</summary>

#	Lesson	Type	Lang
01	[Agent 循环](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](phases/14-agent-engineering/03-reflexion-verbal-rl/)	Build	Python
04	[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](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	[记忆块与睡眠时计算](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	[用 HTN 与进化搜索做规划](phases/14-agent-engineering/11-planning-htn-and-evolutionary/)	Build	Python
12	[Anthropic 的工作流模式](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——基于角色的团队与流程](phases/14-agent-engineering/15-crewai-role-based-crews/)	Build	Python
16	[OpenAI Agents SDK——交接、护栏、追踪](phases/14-agent-engineering/16-openai-agents-sdk/)	Build	Python
17	[Claude Agent SDK——子 agent 与会话存储](phases/14-agent-engineering/17-claude-agent-sdk/)	Build	Python
18	[Agno 与 Mastra——生产级运行时](phases/14-agent-engineering/18-agno-and-mastra-runtimes/)	Learn	Python
19	[基准——SWE-bench、GAIA、AgentBench](phases/14-agent-engineering/19-benchmarks-swebench-gaia/)	Learn	Python
20	[基准——WebArena 与 OSWorld](phases/14-agent-engineering/20-benchmarks-webarena-osworld/)	Learn	Python
21	[操作电脑——Claude、OpenAI CUA、Gemini](phases/14-agent-engineering/21-computer-use-agents/)	Build	Python
22	[语音 agent——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	[Agent 可观测性——Langfuse、Phoenix、Opik](phases/14-agent-engineering/24-agent-observability-platforms/)	Learn	Python
25	[多 agent 辩论与协作](phases/14-agent-engineering/25-multi-agent-debate/)	Build	Python
26	[失败模式——agent 为什么会崩](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	[生产级运行时——队列、事件、Cron](phases/14-agent-engineering/29-production-runtimes/)	Learn	Python
30	[Eval 驱动的 agent 开发](phases/14-agent-engineering/30-eval-driven-agent-development/)	Build	Python
31	[Agent 工作台：能力强的模型为什么仍会失败](phases/14-agent-engineering/31-agent-workbench-why-models-fail/)	Learn	Python
32	[最小化 agent 工作台](phases/14-agent-engineering/32-minimal-agent-workbench/)	Build	Python
33	[把 agent 指令写成可执行约束](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	[给 agent 的初始化脚本](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	[运行时反馈回路](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 agent：把构建者和评判者分开](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	[在真实仓库上跑工作台](phases/14-agent-engineering/41-workbench-for-real-repos/)	Build	Python
42	[综合项目：交付一套可复用的 agent 工作台包](phases/14-agent-engineering/42-agent-workbench-capstone/)	Build	Python

阶段 14 里每节工作台课程（31-42）都附带一份 mission.md，在 agent 打开完整课程文档前先给它做简报。

</details>

<details id="phase-15"> <summary>Phase 15 — 自主系统  <code>22 lessons</code>  长程 agent、自我改进，以及 2026 年的安全技术栈。</summary>

#	Lesson	Type	Lang
01	[从聊天机器人到长程 agent（METR）](phases/15-autonomous-systems/01-long-horizon-agents/)	Learn	Python
02	[STaR、V-STaR、Quiet-STaR：自学推理](phases/15-autonomous-systems/02-star-family-reasoning/)	Learn	Python
03	[AlphaEvolve：进化式编码 agent](phases/15-autonomous-systems/03-alphaevolve-evolutionary-coding/)	Learn	Python
04	[Darwin Gödel Machine：自我修改的 agent](phases/15-autonomous-systems/04-darwin-godel-machine/)	Learn	Python
05	[AI Scientist v2：研讨会级别的科研](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	[递归式自我改进：能力 vs 对齐](phases/15-autonomous-systems/07-recursive-self-improvement/)	Learn	Python
08	[有界自我改进的设计](phases/15-autonomous-systems/08-bounded-self-improvement/)	Learn	Python
09	[自主编码 agent 全景（SWE-bench、CodeAct）](phases/15-autonomous-systems/09-coding-agent-landscape/)	Learn	Python
10	[Claude Code 的权限模式与 Auto 模式](phases/15-autonomous-systems/10-claude-code-permission-modes/)	Learn	Python
11	[浏览器 agent 与间接提示注入](phases/15-autonomous-systems/11-browser-agents/)	Learn	Python
12	[长时运行 agent 的持久化执行](phases/15-autonomous-systems/12-durable-execution/)	Learn	Python
13	[动作预算、迭代上限、成本管控](phases/15-autonomous-systems/13-cost-governors/)	Learn	Python
14	[急停开关、熔断器、金丝雀 token](phases/15-autonomous-systems/14-kill-switches-canaries/)	Learn	Python
15	[人在回路：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	[Constitutional 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 Preparedness 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

</details>

<details id="phase-16"> <summary>Phase 16 — 多 agent 与集群  <code>25 lessons</code>  协调、涌现，以及集体智能。</summary>

#	Lesson	Type	Lang
01	[为什么要多 agent](phases/16-multi-agent-and-swarms/01-why-multi-agent/)	Learn	TypeScript
02	[FIPA-ACL 传承与言语行为](phases/16-multi-agent-and-swarms/02-fipa-acl-heritage/)	Learn	Python
03	[通信协议](phases/16-multi-agent-and-swarms/03-communication-protocols/)	Build	TypeScript
04	[多 agent 原语模型](phases/16-multi-agent-and-swarms/04-primitive-model/)	Learn	Python
05	[Supervisor / 编排者-worker 模式](phases/16-multi-agent-and-swarms/05-supervisor-orchestrator-pattern/)	Build	Python
06	[分层架构与分解漂移](phases/16-multi-agent-and-swarms/06-hierarchical-architecture/)	Learn	Python
07	[心智社会与多 agent 辩论](phases/16-multi-agent-and-swarms/07-society-of-mind-debate/)	Build	Python
08	[角色专精——规划者 / 批评者 / 执行者 / 验证者](phases/16-multi-agent-and-swarms/08-role-specialization/)	Build	Python
09	[并行集群与网络化架构](phases/16-multi-agent-and-swarms/09-parallel-swarm-networks/)	Build	Python
10	[群聊与发言人选择](phases/16-multi-agent-and-swarms/10-group-chat-speaker-selection/)	Build	Python
11	[交接与例程（无状态编排）](phases/16-multi-agent-and-swarms/11-handoffs-and-routines/)	Build	Python
12	[A2A——Agent 到 Agent 协议](phases/16-multi-agent-and-swarms/12-a2a-protocol/)	Build	Python
13	[共享记忆与黑板模式](phases/16-multi-agent-and-swarms/13-shared-memory-blackboard/)	Build	Python
14	[共识与拜占庭容错](phases/16-multi-agent-and-swarms/14-consensus-and-bft/)	Build	Python
15	[投票、自洽性与辩论拓扑](phases/16-multi-agent-and-swarms/15-voting-debate-topology/)	Build	Python
16	[协商与议价](phases/16-multi-agent-and-swarms/16-negotiation-bargaining/)	Build	Python
17	[生成式 agent 与涌现式仿真](phases/16-multi-agent-and-swarms/17-generative-agents-simulation/)	Build	Python
18	[心智理论与涌现式协调](phases/16-multi-agent-and-swarms/18-theory-of-mind-coordination/)	Build	Python
19	[群体优化（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 经济、token 激励、声誉](phases/16-multi-agent-and-swarms/21-agent-economies/)	Learn	Python
22	[生产级扩展——队列、检查点、持久性](phases/16-multi-agent-and-swarms/22-production-scaling-queues-checkpoints/)	Build	Python
23	[失败模式——MAST、群体思维、单一文化](phases/16-multi-agent-and-swarms/23-failure-modes-mast-groupthink/)	Learn	Python
24	[评估与协调基准](phases/16-multi-agent-and-swarms/24-evaluation-coordination-benchmarks/)	Learn	Python
25	[案例研究与 2026 最新进展](phases/16-multi-agent-and-swarms/25-case-studies-2026-sota/)	Learn	Python

</details>

<details id="phase-17"> <summary>Phase 17 — 基础设施与生产  <code>28 lessons</code>  把 AI 交付到真实世界。</summary>

#	Lesson	Type	Lang
01	[托管 LLM 平台 — Bedrock、Azure OpenAI、Vertex AI](phases/17-infrastructure-and-production/01-managed-llm-platforms/)	Learn	Python
02	[推理平台经济学 — Fireworks、Together、Baseten、Modal](phases/17-infrastructure-and-production/02-inference-platform-economics/)	Learn	Python
03	[Kubernetes 上的 GPU 自动扩缩 — Karpenter、KAI Scheduler](phases/17-infrastructure-and-production/03-gpu-autoscaling-kubernetes/)	Learn	Python
04	[vLLM 服务内部机制 — PagedAttention、连续批处理、分块预填充](phases/17-infrastructure-and-production/04-vllm-serving-internals/)	Learn	Python
05	[生产环境中的 EAGLE-3 推测解码](phases/17-infrastructure-and-production/05-eagle3-speculative-decoding/)	Learn	Python
06	[面向前缀密集型负载的 SGLang 与 RadixAttention](phases/17-infrastructure-and-production/06-sglang-radixattention/)	Learn	Python
07	[Blackwell 上用 FP8 与 NVFP4 的 TensorRT-LLM](phases/17-infrastructure-and-production/07-tensorrt-llm-blackwell/)	Learn	Python
08	[推理指标 — TTFT、TPOT、ITL、Goodput、P99](phases/17-infrastructure-and-production/08-inference-metrics-goodput/)	Learn	Python
09	[生产级量化 — AWQ、GPTQ、GGUF、FP8、NVFP4](phases/17-infrastructure-and-production/09-production-quantization/)	Learn	Python
10	[无服务器 LLM 的冷启动缓解](phases/17-infrastructure-and-production/10-cold-start-mitigation/)	Learn	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/)	Learn	Python
12	[边缘推理 — ANE、Hexagon、WebGPU、Jetson](phases/17-infrastructure-and-production/12-edge-inference/)	Learn	Python
13	[LLM 可观测性技术栈选型](phases/17-infrastructure-and-production/13-llm-observability/)	Learn	Python
14	[提示缓存与语义缓存的经济学](phases/17-infrastructure-and-production/14-prompt-semantic-caching/)	Learn	Python
15	[批处理 API — 50% 折扣作为行业标准](phases/17-infrastructure-and-production/15-batch-apis/)	Learn	Python
16	[把模型路由作为降本原语](phases/17-infrastructure-and-production/16-model-routing/)	Learn	Python
17	[预填充/解码分离 — NVIDIA Dynamo 与 llm-d](phases/17-infrastructure-and-production/17-disaggregated-prefill-decode/)	Learn	Python
18	[带 LMCache KV 卸载的 vLLM 生产栈](phases/17-infrastructure-and-production/18-vllm-production-stack-lmcache/)	Learn	Python
19	[AI 网关 — LiteLLM、Portkey、Kong、Bifrost](phases/17-infrastructure-and-production/19-ai-gateways/)	Learn	Python
20	[影子、金丝雀与渐进式部署](phases/17-infrastructure-and-production/20-shadow-canary-progressive/)	Learn	Python
21	[LLM 功能的 A/B 测试 — GrowthBook 与 Statsig](phases/17-infrastructure-and-production/21-ab-testing-llm-features/)	Learn	Python
22	[LLM API 的负载测试 — k6、LLMPerf、GenAI-Perf](phases/17-infrastructure-and-production/22-load-testing-llm-apis/)	Build	Python
23	[面向 AI 的 SRE — 多智能体事件响应](phases/17-infrastructure-and-production/23-sre-for-ai/)	Learn	Python
24	[面向 LLM 生产的混沌工程](phases/17-infrastructure-and-production/24-chaos-engineering-llm/)	Learn	Python
25	[安全 — 密钥、PII 脱敏、审计日志](phases/17-infrastructure-and-production/25-security-secrets-audit/)	Learn	Python
26	[合规 — SOC 2、HIPAA、GDPR、EU AI Act、ISO 42001](phases/17-infrastructure-and-production/26-compliance-frameworks/)	Learn	Python
27	[面向 LLM 的 FinOps — 单位经济与多租户归因](phases/17-infrastructure-and-production/27-finops-llms/)	Learn	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/)	Learn	Python

</details>

<details id="phase-18"> <summary>Phase 18 — 伦理、安全与对齐  <code>30 lessons</code>  构建对人类有益的 AI。这不是选修。</summary>

#	Lesson	Type	Lang
01	[把遵循指令当作对齐信号](phases/18-ethics-safety-alignment/01-instruction-following-alignment-signal/)	Learn	Python
02	[奖励黑客与古德哈特定律](phases/18-ethics-safety-alignment/02-reward-hacking-goodhart/)	Learn	Python
03	[直接偏好优化家族](phases/18-ethics-safety-alignment/03-direct-preference-optimization-family/)	Learn	Python
04	[阿谀奉承：RLHF 的放大效应](phases/18-ethics-safety-alignment/04-sycophancy-rlhf-amplification/)	Learn	Python
05	[Constitutional AI 与 RLAIF](phases/18-ethics-safety-alignment/05-constitutional-ai-rlaif/)	Learn	Python
06	[Mesa 优化与欺骗性对齐](phases/18-ethics-safety-alignment/06-mesa-optimization-deceptive-alignment/)	Learn	Python
07	[潜伏 agent——持续性欺骗](phases/18-ethics-safety-alignment/07-sleeper-agents-persistent-deception/)	Learn	Python
08	[前沿模型中的上下文内谋划](phases/18-ethics-safety-alignment/08-in-context-scheming-frontier-models/)	Learn	Python
09	[对齐造假](phases/18-ethics-safety-alignment/09-alignment-faking/)	Learn	Python
10	[AI Control——即便被颠覆也保安全](phases/18-ethics-safety-alignment/10-ai-control-subversion/)	Learn	Python
11	[可扩展监督与弱到强](phases/18-ethics-safety-alignment/11-scalable-oversight-weak-to-strong/)	Learn	Python
12	[红队：PAIR 与自动化攻击](phases/18-ethics-safety-alignment/12-red-teaming-pair-automated-attacks/)	Build	Python
13	[多样本越狱](phases/18-ethics-safety-alignment/13-many-shot-jailbreaking/)	Learn	Python
14	[ASCII 字符画与视觉越狱](phases/18-ethics-safety-alignment/14-ascii-art-visual-jailbreaks/)	Build	Python
15	[间接提示注入](phases/18-ethics-safety-alignment/15-indirect-prompt-injection/)	Build	Python
16	[红队工具：Garak、Llama Guard、PyRIT](phases/18-ethics-safety-alignment/16-red-team-tooling-garak-llamaguard-pyrit/)	Build	Python
17	[WMDP 与双用途能力评估](phases/18-ethics-safety-alignment/17-wmdp-dual-use-evaluation/)	Learn	Python
18	[前沿安全框架——RSP、PF、FSF](phases/18-ethics-safety-alignment/18-frontier-safety-frameworks-rsp-pf-fsf/)	Learn	Python
19	[模型福祉研究](phases/18-ethics-safety-alignment/19-model-welfare-research/)	Learn	Python
20	[偏见与表征伤害](phases/18-ethics-safety-alignment/20-bias-representational-harm/)	Build	Python
21	[公平性准则：群体、个体、反事实](phases/18-ethics-safety-alignment/21-fairness-criteria-group-individual-counterfactual/)	Learn	Python
22	[面向 LLM 的差分隐私](phases/18-ethics-safety-alignment/22-differential-privacy-for-llms/)	Build	Python
23	[水印：SynthID、Stable Signature、C2PA](phases/18-ethics-safety-alignment/23-watermarking-synthid-stable-signature-c2pa/)	Build	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/)	Learn	Python
25	[EchoLeak 与 AI 的 CVE](phases/18-ethics-safety-alignment/25-echoleak-cves-for-ai/)	Learn	Python
26	[模型卡、系统卡与数据集卡](phases/18-ethics-safety-alignment/26-model-system-dataset-cards/)	Build	Python
27	[数据溯源与训练数据治理](phases/18-ethics-safety-alignment/27-data-provenance-training-governance/)	Learn	Python
28	[对齐研究生态：MATS、Redwood、Apollo、METR](phases/18-ethics-safety-alignment/28-alignment-research-ecosystem/)	Learn	Python
29	[内容审核系统：OpenAI、Perspective、Llama Guard](phases/18-ethics-safety-alignment/29-moderation-systems-openai-perspective-llamaguard/)	Build	Python
30	[双用途风险：网络、生物、化学、核](phases/18-ethics-safety-alignment/30-dual-use-risk-cyber-bio-chem-nuclear/)	Learn	Python

</details>

<details id="phase-19"> <summary>Phase 19 — 综合项目  <code>85 projects</code>  2026 年的端到端可交付产品，每个 20-40 小时。</summary>

#	Project	Combines	Lang
01	[终端原生编码 agent](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	[自主科研 agent（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 agent](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（受监管垂直行业）](phases/19-capstone-projects/08-production-rag-chatbot/)	P5 P7 P11 P12 P17 P18	Python
09	[代码迁移 agent（仓库级升级）](phases/19-capstone-projects/09-code-migration-agent/)	P5 P7 P11 P13 P14 P15 P17	Python
10	[多 agent 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 Eval 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 server](phases/19-capstone-projects/13-mcp-server-with-registry/)	P11 P13 P14 P17 P18	Python
14	[投机解码推理服务器](phases/19-capstone-projects/14-speculative-decoding-server/)	P3 P7 P10 P17	Python
15	[Constitutional 安全测试架 + 红队靶场](phases/19-capstone-projects/15-constitutional-safety-harness/)	P10 P11 P13 P14 P18	Python
16	[GitHub Issue 到 PR 的自主 agent](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
20	[Agent Harness Loop 契约](phases/19-capstone-projects/20-agent-harness-loop-contract/)	A. Agent harness	Python
21	[带 Schema 校验的 Tool Registry](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	[Function Call Dispatcher](phases/19-capstone-projects/23-function-call-dispatcher/)	A. Agent harness	Python
24	[Plan-Execute 控制流](phases/19-capstone-projects/24-plan-execute-control-flow/)	A. Agent harness	Python
25	[Verification Gate 与 Observation Budget](phases/19-capstone-projects/25-verification-gates-observation-budget/)	A. Agent harness	Python
26	[带 Denylist 与 Path Jail 的 Sandbox Runner](phases/19-capstone-projects/26-sandbox-runner-denylist/)	A. Agent harness	Python
27	[带 Fixture Tasks 的 Eval Harness](phases/19-capstone-projects/27-eval-harness-fixture-tasks/)	A. Agent harness	Python
28	[用 OTel GenAI Span 与 Prometheus 做 Observability](phases/19-capstone-projects/28-observability-otel-traces/)	A. Agent harness	Python
29	[端到端 Coding Agent Demo](phases/19-capstone-projects/29-end-to-end-coding-task-demo/)	A. Agent harness	Python
30	[从零实现 BPE Tokenizer](phases/19-capstone-projects/30-bpe-tokenizer-from-scratch/)	B. NLP LLM	Python
31	[带 Sliding Window 的 Tokenized Dataset](phases/19-capstone-projects/31-tokenized-dataset-sliding-window/)	B. NLP LLM	Python
32	[Token Embedding 与 Positional Embedding](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	[从零实现 Transformer Block](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	[通过换 Head 做分类微调](phases/19-capstone-projects/38-classifier-finetuning/)	B. NLP LLM	Python
39	[通过 SFT 做 Instruction Tuning](phases/19-capstone-projects/39-instruction-tuning-sft/)	B. NLP LLM	Python
40	[从零实现 DPO](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. 端到端训练	Python
43	[HDF5 Tokenized Corpus](phases/19-capstone-projects/43-hdf5-tokenized-corpus/)	C. 端到端训练	Python

| 44 | [Cosine 学习率 + 线性 Warmup](phases/19-capstone-projects/44-cosine-lr-warmup/) | C. 端到端训练 | Pyth

🎯 aiskill88 AI 点评 A 级 2026-06-26

全面系统的AI工程学习资源

⚡ 核心功能

通过标准 MCP 协议与 Claude、Cursor 等主流 AI 客户端深度集成
提供结构化工具调用接口，显著降低 AI 集成复杂度
支持 Claude Desktop 和 Claude Code 无缝接入，开箱即用
可与其他 MCP 工具组合叠加，构建完整 AI 工作站
轻量无侵入设计，不影响现有系统架构

👥 适合人群

Claude Desktop / Claude Code 用户AI 工具开发者需要扩展 AI 能力的专业人士自动化工程师

🎯 使用场景

在 Claude Desktop 对话中直接调用本地工具，实现 AI 与系统的深度联动
通过自然语言驱动复杂的多步骤自动化任务，代替繁琐手动操作
将多个 MCP 工具组合使用，构建个人专属 AI 工作站

⚖️ 优点与不足

✅ 优点

+MIT 协议，可免费商用
+标准化 MCP 协议，生态互联性强
+与 Claude 官方生态无缝对接
+即插即用，配置简单快捷

⚠️ 不足

−依赖 Claude 客户端，非 Claude 用户无法使用
−MCP 协议仍在持续演进，接口可能变更
−需要一定的配置步骤

⚠️ 使用须知

AI Skill Hub 为第三方内容聚合平台，本页面信息基于公开数据整理，不对工具功能和质量作任何法律背书。

建议在沙箱或测试环境中充分验证后，再部署至生产环境，并做好必要的安全评估。

📄 License 说明

🔗 相关工具推荐

github-mcp-server MCP工具

GitHub官方MCP服务器实现，使AI助手能直接操作GitHub仓库、问题、拉取请求等资源。采用Go语言开发，高性能稳

mcp-use MCP工具

MCP工具

🧩 你可能还需要

基于当前 Skill 的能力图谱，自动补全的工具组合

技能寻求者

MCP · Agent · 工作流

natively-cluely-ai-assistant — Claude Skill 中文使用文档

免费开源的AI面试助手，实时转录，隐蔽模式，局部RAG，BYOK。无订阅，防止数据泄露。

为Claude Code设计的开源MCP工具集，包含108个MCP工具和40+智能体模板。支持多智能体协作编排，提供完整的自主代理框架。适合

LEANN AI技能包

MCP · Agent · 工作流

❓ 常见问题 FAQ

如何成为AI Age−

学习和实践AI工程相关知识和技能

MCP 是什么？和普通 API 有什么区别？+

我需要编程基础才能使用这个 MCP 工具吗？+

这个工具支持 Claude Code 吗？还是只有 Claude Desktop？+

MCP 工具是否会访问我的本地文件或数据？+

多个 MCP 工具可以同时使用吗？+

💡 AI Skill Hub 点评

经综合评估，AI工程从零到精通在MCP工具赛道中表现稳健，质量优秀。如果你已有明确的使用需求，可以直接上手体验；如果还在评估阶段，建议对比同类工具后再做决策。

⬇️ 获取与下载

⬇ 下载源码 ZIP

✅ MIT 协议 · 可免费商用 · 直接从 aiskill88 服务器下载，无需跳转 GitHub

📚 深入学习 AI工程从零到精通

查看分步骤安装教程和完整使用指南，快速上手这款工具

⚙️ 安装教程 📚 使用教程

🌐 原始信息

原始名称	`ai-engineering-from-scratch-zh`
Topics	`aiai-agentsai-engineeringpythonchinese`
GitHub	https://github.com/fancyboi999/ai-engineering-from-scratch-zh
License	MIT
语言	Python