bojieli/ai-agent-bookPublic

《深入理解 AI Agent:设计原理与工程实践》(李博杰 著)开源主仓库:全书正文、编译版 PDF 与按章配套代码

AI summary: An open-source, comprehensive book on building and understanding AI agents.

Stars
34K
+1.4K today
Forks
3.7K
Watchers
131
Open issues
2
Open PRs
0
Contributors
~55
Commits
1.4K
Branches
122

PythonApache-2.0Created Sep 9, 2025Last push today+6K stars this week+11.4K this month

Star history

since Jul 12, 2026
010K20K30KJul 2026Jul 2026Jul 2026Aug 2026
34K stars as of Aug 7, 2026, tracked back to Jul 12, 2026. Historical curve reconstructed from public GitHub event archives, calibrated to the current total.

Contribution activity

commits per day, last 52 weeks
AugSepOctNovDecJanFebMarAprMayJunJulAugMonWedFri2025-08-10: 0 commits2025-08-11: 0 commits2025-08-12: 0 commits2025-08-13: 0 commits2025-08-14: 0 commits2025-08-15: 0 commits2025-08-16: 0 commits2025-08-17: 0 commits2025-08-18: 0 commits2025-08-19: 0 commits2025-08-20: 0 commits2025-08-21: 0 commits2025-08-22: 0 commits2025-08-23: 0 commits2025-08-24: 0 commits2025-08-25: 0 commits2025-08-26: 0 commits2025-08-27: 0 commits2025-08-28: 0 commits2025-08-29: 0 commits2025-08-30: 0 commits2025-08-31: 0 commits2025-09-01: 0 commits2025-09-02: 0 commits2025-09-03: 0 commits2025-09-04: 0 commits2025-09-05: 0 commits2025-09-06: 0 commits2025-09-07: 0 commits2025-09-08: 0 commits2025-09-09: 3 commits2025-09-10: 2 commits2025-09-11: 2 commits2025-09-12: 1 commit2025-09-13: 3 commits2025-09-14: 8 commits2025-09-15: 0 commits2025-09-16: 7 commits2025-09-17: 5 commits2025-09-18: 1 commit2025-09-19: 0 commits2025-09-20: 0 commits2025-09-21: 4 commits2025-09-22: 1 commit2025-09-23: 3 commits2025-09-24: 12 commits2025-09-25: 7 commits2025-09-26: 1 commit2025-09-27: 0 commits2025-09-28: 0 commits2025-09-29: 0 commits2025-09-30: 8 commits2025-10-01: 2 commits2025-10-02: 5 commits2025-10-03: 0 commits2025-10-04: 18 commits2025-10-05: 5 commits2025-10-06: 7 commits2025-10-07: 4 commits2025-10-08: 0 commits2025-10-09: 0 commits2025-10-10: 0 commits2025-10-11: 0 commits2025-10-12: 1 commit2025-10-13: 0 commits2025-10-14: 0 commits2025-10-15: 0 commits2025-10-16: 0 commits2025-10-17: 2 commits2025-10-18: 1 commit2025-10-19: 1 commit2025-10-20: 0 commits2025-10-21: 0 commits2025-10-22: 0 commits2025-10-23: 0 commits2025-10-24: 0 commits2025-10-25: 0 commits2025-10-26: 1 commit2025-10-27: 2 commits2025-10-28: 4 commits2025-10-29: 0 commits2025-10-30: 0 commits2025-10-31: 0 commits2025-11-01: 0 commits2025-11-02: 0 commits2025-11-03: 0 commits2025-11-04: 0 commits2025-11-05: 0 commits2025-11-06: 0 commits2025-11-07: 0 commits2025-11-08: 0 commits2025-11-09: 0 commits2025-11-10: 2 commits2025-11-11: 0 commits2025-11-12: 0 commits2025-11-13: 0 commits2025-11-14: 0 commits2025-11-15: 0 commits2025-11-16: 0 commits2025-11-17: 0 commits2025-11-18: 0 commits2025-11-19: 0 commits2025-11-20: 0 commits2025-11-21: 0 commits2025-11-22: 0 commits2025-11-23: 0 commits2025-11-24: 0 commits2025-11-25: 0 commits2025-11-26: 0 commits2025-11-27: 0 commits2025-11-28: 0 commits2025-11-29: 0 commits2025-11-30: 0 commits2025-12-01: 0 commits2025-12-02: 0 commits2025-12-03: 0 commits2025-12-04: 0 commits2025-12-05: 0 commits2025-12-06: 0 commits2025-12-07: 0 commits2025-12-08: 0 commits2025-12-09: 0 commits2025-12-10: 0 commits2025-12-11: 0 commits2025-12-12: 0 commits2025-12-13: 0 commits2025-12-14: 0 commits2025-12-15: 0 commits2025-12-16: 0 commits2025-12-17: 0 commits2025-12-18: 1 commit2025-12-19: 0 commits2025-12-20: 0 commits2025-12-21: 0 commits2025-12-22: 0 commits2025-12-23: 0 commits2025-12-24: 0 commits2025-12-25: 0 commits2025-12-26: 0 commits2025-12-27: 0 commits2025-12-28: 0 commits2025-12-29: 0 commits2025-12-30: 0 commits2025-12-31: 0 commits2026-01-01: 0 commits2026-01-02: 0 commits2026-01-03: 0 commits2026-01-04: 0 commits2026-01-05: 0 commits2026-01-06: 0 commits2026-01-07: 0 commits2026-01-08: 0 commits2026-01-09: 0 commits2026-01-10: 0 commits2026-01-11: 0 commits2026-01-12: 0 commits2026-01-13: 0 commits2026-01-14: 0 commits2026-01-15: 0 commits2026-01-16: 0 commits2026-01-17: 0 commits2026-01-18: 0 commits2026-01-19: 0 commits2026-01-20: 0 commits2026-01-21: 0 commits2026-01-22: 0 commits2026-01-23: 0 commits2026-01-24: 0 commits2026-01-25: 0 commits2026-01-26: 0 commits2026-01-27: 0 commits2026-01-28: 0 commits2026-01-29: 0 commits2026-01-30: 0 commits2026-01-31: 0 commits2026-02-01: 0 commits2026-02-02: 0 commits2026-02-03: 0 commits2026-02-04: 0 commits2026-02-05: 0 commits2026-02-06: 0 commits2026-02-07: 0 commits2026-02-08: 0 commits2026-02-09: 0 commits2026-02-10: 0 commits2026-02-11: 0 commits2026-02-12: 0 commits2026-02-13: 0 commits2026-02-14: 0 commits2026-02-15: 0 commits2026-02-16: 0 commits2026-02-17: 0 commits2026-02-18: 0 commits2026-02-19: 0 commits2026-02-20: 0 commits2026-02-21: 0 commits2026-02-22: 0 commits2026-02-23: 0 commits2026-02-24: 0 commits2026-02-25: 0 commits2026-02-26: 0 commits2026-02-27: 0 commits2026-02-28: 0 commits2026-03-01: 0 commits2026-03-02: 0 commits2026-03-03: 0 commits2026-03-04: 0 commits2026-03-05: 0 commits2026-03-06: 0 commits2026-03-07: 0 commits2026-03-08: 0 commits2026-03-09: 0 commits2026-03-10: 0 commits2026-03-11: 0 commits2026-03-12: 0 commits2026-03-13: 0 commits2026-03-14: 0 commits2026-03-15: 0 commits2026-03-16: 0 commits2026-03-17: 0 commits2026-03-18: 0 commits2026-03-19: 0 commits2026-03-20: 0 commits2026-03-21: 0 commits2026-03-22: 0 commits2026-03-23: 0 commits2026-03-24: 0 commits2026-03-25: 0 commits2026-03-26: 0 commits2026-03-27: 0 commits2026-03-28: 0 commits2026-03-29: 0 commits2026-03-30: 0 commits2026-03-31: 0 commits2026-04-01: 0 commits2026-04-02: 0 commits2026-04-03: 0 commits2026-04-04: 0 commits2026-04-05: 0 commits2026-04-06: 0 commits2026-04-07: 0 commits2026-04-08: 0 commits2026-04-09: 0 commits2026-04-10: 0 commits2026-04-11: 0 commits2026-04-12: 0 commits2026-04-13: 0 commits2026-04-14: 0 commits2026-04-15: 0 commits2026-04-16: 0 commits2026-04-17: 0 commits2026-04-18: 0 commits2026-04-19: 0 commits2026-04-20: 0 commits2026-04-21: 0 commits2026-04-22: 0 commits2026-04-23: 0 commits2026-04-24: 0 commits2026-04-25: 0 commits2026-04-26: 0 commits2026-04-27: 0 commits2026-04-28: 0 commits2026-04-29: 0 commits2026-04-30: 0 commits2026-05-01: 0 commits2026-05-02: 0 commits2026-05-03: 0 commits2026-05-04: 0 commits2026-05-05: 0 commits2026-05-06: 0 commits2026-05-07: 0 commits2026-05-08: 0 commits2026-05-09: 0 commits2026-05-10: 0 commits2026-05-11: 0 commits2026-05-12: 0 commits2026-05-13: 0 commits2026-05-14: 0 commits2026-05-15: 0 commits2026-05-16: 0 commits2026-05-17: 0 commits2026-05-18: 0 commits2026-05-19: 0 commits2026-05-20: 0 commits2026-05-21: 0 commits2026-05-22: 0 commits2026-05-23: 0 commits2026-05-24: 0 commits2026-05-25: 0 commits2026-05-26: 0 commits2026-05-27: 0 commits2026-05-28: 0 commits2026-05-29: 0 commits2026-05-30: 0 commits2026-05-31: 0 commits2026-06-01: 0 commits2026-06-02: 0 commits2026-06-03: 0 commits2026-06-04: 0 commits2026-06-05: 0 commits2026-06-06: 0 commits2026-06-07: 0 commits2026-06-08: 0 commits2026-06-09: 0 commits2026-06-10: 0 commits2026-06-11: 0 commits2026-06-12: 0 commits2026-06-13: 0 commits2026-06-14: 0 commits2026-06-15: 0 commits2026-06-16: 0 commits2026-06-17: 0 commits2026-06-18: 0 commits2026-06-19: 0 commits2026-06-20: 0 commits2026-06-21: 0 commits2026-06-22: 0 commits2026-06-23: 0 commits2026-06-24: 0 commits2026-06-25: 0 commits2026-06-26: 0 commits2026-06-27: 0 commits2026-06-28: 0 commits2026-06-29: 0 commits2026-06-30: 0 commits2026-07-01: 0 commits2026-07-02: 0 commits2026-07-03: 0 commits2026-07-04: 0 commits2026-07-05: 0 commits2026-07-06: 0 commits2026-07-07: 0 commits2026-07-08: 0 commits2026-07-09: 0 commits2026-07-10: 0 commits2026-07-11: 0 commits2026-07-12: 0 commits2026-07-13: 0 commits2026-07-14: 0 commits2026-07-15: 14 commits2026-07-16: 1 commit2026-07-17: 42 commits2026-07-18: 72 commits2026-07-19: 31 commits2026-07-20: 56 commits2026-07-21: 116 commits2026-07-22: 135 commits2026-07-23: 80 commits2026-07-24: 46 commits2026-07-25: 40 commits2026-07-26: 28 commits2026-07-27: 23 commits2026-07-28: 45 commits2026-07-29: 67 commits2026-07-30: 81 commits2026-07-31: 70 commits2026-08-01: 18 commits2026-08-02: 17 commits2026-08-03: 19 commits2026-08-04: 14 commits2026-08-05: 23 commits2026-08-06: 28 commits2026-08-07: 6 commits2026-08-08: 0 commits
1,196 commits in the last yearLessMore

Signals and awards

derived from tracked data
  • Widely adopted

    33,975 stars

  • Rising fast

    +5,992 stars this week

  • Very active

    1,196 commits in 52 weeks

  • Permissive license

    Apache-2.0

  • Continuous integration

    Automated checks passing

  • Repeat trending

    16 trending appearances

What ai-agent-book does

This repository hosts the source code and content for an in-depth, open-source book dedicated to the architecture, design, and implementation of AI agents. It covers the evolution of agents from simple prompt engineering to complex, multi-agent systems capable of autonomous reasoning and tool use. The book explains core concepts like memory management, planning algorithms (e.g., ReAct, Plan-and-Solve), and evaluation metrics. It bridges theoretical research with practical implementation, providing code snippets and architectural diagrams for developers building real-world agentic applications.

Software developers, AI researchers, and tech enthusiasts who want a deep, structured understanding of AI agents. Requires basic programming knowledge.

  • Comprehensive Curriculum: Covers everything from basic LLM concepts to advanced multi-agent orchestration.
  • Practical Code Examples: Includes working examples of different agent architectures using modern frameworks.
  • Architectural Deep Dives: Explains the internal mechanics of popular agent patterns like ReAct and AutoGPT.
  • Open Source Collaboration: Content is written in Markdown and open for community contributions and corrections.
  • Evaluation Methodologies: Teaches how to properly benchmark and test the reliability of autonomous agents.

Where teams use it

Learning Agent Architecture

Software engineers read the book to understand how to design robust, autonomous AI systems beyond simple chatbots.

Academic Reference

Students and researchers use the material as a structured guide to the current state-of-the-art in agentic AI.

Framework Evaluation

Developers use the architectural breakdowns to decide which agent framework fits their needs.

Community Contribution

Experts in the field submit pull requests to update chapters with the latest research and methodologies.

Getting started: Read the content online via the provided GitHub Pages link or clone the repo to read the Markdown files locally.

README

main branch

深入理解 AI Agent:设计原理与工程实践

PDF 在线阅读 Stars License Languages Trending GitHub Project of the Day

中文 ← 当前 · English · Español · Bahasa Indonesia · العربية · 繁體中文(台灣) · Русский · Tiếng Việt · தமிழ் · 日本語 · Türkçe · 한국어 · Magyar

📥 下载 PDF / EPUB(推荐)— 推荐使用 PDF / EPUB 离线阅读,排版最佳;也可在线阅读(支持多语言切换、章节折叠、全文搜索,每次推送自动更新)。

Agent = LLM + 上下文 + 工具——本书围绕这个核心公式,用 10 章把 AI Agent 从原理讲到工程实战。全书正文、配图、95 个配套实验全部开源,欢迎亲手把实验跑一遍。

📚 10 章 正文,从基础到生产 📂 95 个 配套实验(含本地项目与外部复现轨道) 🌐 13 种 语言:中 / 英 / 西 / 印尼 / 阿 / 繁體中文(台灣) / 俄 / 泰米尔 / 越 / 日 / 土耳其 / 韩 / 匈牙利

📖 电子书

📥 离线下载(推荐,全书正文,开源免费)。以下链接始终指向 main 分支的最新构建;固定版本见 Releases

🌐 也可在线阅读 — 支持多语言切换、章节折叠、全文搜索、配套实验直达,每次 main 分支推送后自动重新构建。

中文正文源码位于 book/;英文/西班牙语/印度尼西亚语/阿拉伯语/繁體中文(台灣)/俄语/泰米尔/越南语/日语/土耳其语/韩语/匈牙利语版本为社区贡献(可能滞后于中文原版),分别位于 book-en/book-es/book-id/book-ar/book-zhtw/book-ru/book-ta/book-vi/book-ja/book-tr/book-ko/book-hu/

🔧 想自行编译 PDF / EPUB?(PDF 需 pandoc / xelatex / ElegantBook)
  • EPUB:使用统一的构建脚本,详情请参阅 EPUB 构建说明

  • 正文源码book/introduction.md(引言)、book/chapter1.md ~ book/chapter10.md(第一至第十章)、book/afterword.md(后记)

  • 编译:安装 pandoc、xelatex、ElegantBook 文档类与相关字体后,运行

    cd book && bash build_pdf.sh

    图表以 SVG 文件存于 book/images/,编译时直接使用;排版细节见 book/preamble.texbook/*.lua

📑 内容速览(第 1–10 章)

全书围绕核心公式 Agent = LLM + 上下文 + 工具 展开,十章层层递进:

主题 一句话核心 正文 代码
1 🚀 Agent 基础知识 Agent = LLM + 上下文 + 工具;Harness 工程才是竞争力 4
2 🎯 上下文工程 上下文决定能力上限:KV Cache、提示工程、Agent Skills、上下文压缩 9
3 📚 用户记忆和知识库 跨会话记住用户、接入外部知识:用户记忆、RAG、结构化索引、知识图谱 13
4 🛠️ 工具 工具是 Agent 的双手:MCP 协议、感知/执行/协作三类工具、事件驱动异步 Agent、主动工具发现 7
5 💻 Coding Agent 与代码生成 代码是「能创造新工具的工具」,生产级 Coding Agent 全景 13
6 🎯 Agent 的评估 把表现变成可比较信号:评估环境、指标、统计显著性、评估驱动选型 13
7 🧠 模型后训练 预训练/SFT/RL 三阶段:何时选 SFT、何时选 RL,工具调用内化、样本效率 16
8 🔄 Agent 的持续进化 从运行轨迹获得学习信号,更新知识、指令、程序与参数 9
9 🎙️ 多模态与实时交互 从文本扩展到语音、GUI、物理世界:语音三范式、Computer Use、机器人 10
10 🤝 多 Agent 协作 群体智能高于个体:协作框架、上下文共享/隔离、涌现的「Agent 社会」 8

💡 = 在 GitHub 网页直接读章节正文(markdown);N = 该章配套项目数,点击查看代码。项目类型说明(✅ 可运行 / 📖 复现 / 🚧 设计)见各章 README。

📚 如何高效阅读本书?详见 学习建议(核心理念、学习路径、难度分级、实践建议)。

💻 运行配套实验

项目统一支持 Python 3.10+。请在仓库根目录按章节安装依赖;将 ch1 替换为 ch2 ~ ch10 即可安装对应章节:

# 推荐:使用提交到仓库的 uv.lock,获得可复现的章节环境
uv sync --locked --extra ch1

# 未安装 uv 时:使用 pip 从 pyproject.toml 重新解析
python -m pip install -e ".[ch1]"

运行会调用模型的实验前,请按该实验 README 配置凭据:支持根目录配置的实验可复制 .env.example.env 并填入至少一个提供商 Key;有些实验要求在自身目录放 .env 或直接导出环境变量。只有在实验 README 或 CLI 明确列出 ollama 时,才可启动本地 Ollama 并添加 --provider ollama

安装后可从仓库根目录运行实验,例如:

uv run python chapter1/context/main.py
# 使用 pip 安装时也可直接运行:python chapter1/context/main.py
  • uv 安装方法见 官方文档pip 仍受支持,但不会使用锁文件。
  • 各实验现有的 requirements.txt 在迁移期间继续有效,适合只运行单个项目或需要特殊版本约束的情况。
  • all 是不含本地训练栈的 CPU 友好组合,并不代表每个实验;uv sync 每次都会精确同步当前选择,使用特殊 extra 时请合并到同一条命令,例如 uv sync --locked --extra ch2 --extra vllmuv sync --locked --extra ch7 --extra unsloth;pip 对应为 python -m pip install -e ".[ch2,vllm]"
  • 浏览器、CUDA、FFmpeg、Ollama、Playwright 浏览器及外部仓库等系统依赖,请继续参考各实验 README。部分浏览器和记忆实验需要 Python 3.11+,第 8 章部分内置第三方组件需要 Python 3.12+。

🔑 API 密钥

建议申请下面几个平台的 API Key 方便学习。模型选型可参考 这篇指南

平台 链接 特色 访问节点
Kimi(月之暗面) https://platform.moonshot.cn/ Kimi 系列,Coding、Agent 能力强 中国大陆
智谱 GLM https://open.bigmodel.cn/ GLM-5.2 等,Coding、Agent 能力强 中国大陆
Siliconflow https://siliconflow.cn/ 各种开源模型(DeepSeek、Qwen 等),中国大陆访问速度快 中国大陆
DeepSeek https://platform.deepseek.com/ DeepSeek 官方 API 全球 + 中国大陆
Krill AI www.krill-ai.net 一站式访问全球及国内主流模型(OpenAI、Claude、Gemini、Grok、Kimi、GLM、DeepSeek、Qwen、Minimax) 全球 + 中国大陆
OpenRouter https://openrouter.ai/ 一站式访问全球及国内主流模型(GPT、Claude、Gemini、Kimi、GLM、DeepSeek、Qwen 等) 全球

💎 赞助商

感谢 Krill AI 赞助本项目!Krill 提供 GPT / Claude / Gemini / 多款国产模型的官方稳定极速 API 中转服务,支持企业级定制、报销开票、7×16h 专属技术支持,更有独家适配的 WebSocket 连接方式,畅享极速首字速度。

Krill 为本书读者提供特别优惠:使用此链接注册并在充值时填写优惠码「ai-agent-book」,首次购买 Codex 套餐可享 77 折优惠!

🧪 配套实验的执行状态、证据与未完成门禁单独记录在 docs/EXPERIMENT_STATUS.md;克隆或安装源码不代表实验完成。

📦 附录 · 外部仓库获取

本附录列出第 6、7、9、10 章与实验直接映射的 22 个外部仓库,另含 1 个辅助训练 cookbook;它们不作为本书源码内置依赖(出于体积与版权),需要自行克隆到对应目录。部分训练项目还会按各自 README 拉取模型、数据集和模拟器依赖,不计入这 22 个直接映射。以下版本来自 2026-07-30 工作区 checkout 或同日只读上游审计;固定源码只建立复现起点,不代表训练、硬件、浏览器或多 Agent 实验已经执行。

一键克隆脚本

🔧 展开克隆命令(共 23 个 checkout:22 个实验映射 + 1 个辅助 cookbook)
# 第 6 章 · 评测基准
git clone https://github.com/google-research/android_world.git chapter6/android_world && git -C chapter6/android_world checkout --detach 0e95d641e244504c22087cc29b013f3b2428a261
git clone https://huggingface.co/datasets/gaia-benchmark/GAIA chapter6/GAIA && git -C chapter6/GAIA checkout --detach 682dd723ee1e1697e00360edccf2366dc8418dd9
git clone https://github.com/xlang-ai/OSWorld.git chapter6/OSWorld && git -C chapter6/OSWorld checkout --detach 8365edc975efd0477a0d62444a5beed562ab5a7b
git clone https://github.com/SWE-bench/SWE-bench.git chapter6/SWE-bench && git -C chapter6/SWE-bench checkout --detach 5cd4be9fb23971679cbbafe5a0ecade27cef99be
git clone https://github.com/sierra-research/tau2-bench.git chapter6/tau2-bench && git -C chapter6/tau2-bench checkout --detach 8d005b0e5b9e4af0bc055886fa7f95fc86d1710e
git clone https://github.com/laude-institute/terminal-bench.git chapter6/terminal-bench && git -C chapter6/terminal-bench checkout --detach 8384a179b1b8688f6ea5233a4d9d51218df1ac96

# 第 7 章 · 训练框架(bojieli/* 为本书适配的分支)
git clone https://github.com/bojieli/minimind.git chapter7/MiniMind-pretrain/minimind && git -C chapter7/MiniMind-pretrain/minimind fetch origin 8bdc5d97d5845a8c1ac2ed56a5b8b4c0d0fb0795 && git -C chapter7/MiniMind-pretrain/minimind checkout --detach 8bdc5d97d5845a8c1ac2ed56a5b8b4c0d0fb0795 && test "$(git -C chapter7/MiniMind-pretrain/minimind rev-parse HEAD)" = "8bdc5d97d5845a8c1ac2ed56a5b8b4c0d0fb0795"  # 实验 7-3
git clone https://github.com/bojieli/minimind-v.git chapter7/MiniMind-pretrain/minimind-v && git -C chapter7/MiniMind-pretrain/minimind-v fetch origin ead791c530fa5f9a3549dbfe9e11ec732d18d2e5 && git -C chapter7/MiniMind-pretrain/minimind-v checkout --detach ead791c530fa5f9a3549dbfe9e11ec732d18d2e5 && test "$(git -C chapter7/MiniMind-pretrain/minimind-v rev-parse HEAD)" = "ead791c530fa5f9a3549dbfe9e11ec732d18d2e5"  # 实验 7-4
git clone https://github.com/bojieli/AdaptThink.git chapter7/AdaptThink-original && git -C chapter7/AdaptThink-original checkout --detach 0033ad172dd53ac64004b763477407014f21b838  # 实验 7-10
git clone https://github.com/bojieli/SFTvsRL.git chapter7/SFTvsRL && git -C chapter7/SFTvsRL checkout --detach fef0a4a3367260a0934be1e40b01e4021698e023  # 实验 7-11、7-12
git clone https://github.com/bojieli/AWorld.git chapter7/AWorld && git -C chapter7/AWorld checkout --detach a52d61d6d483e66b22ef16970eae5bbf4f4ab2ec  # 实验 7-15
git clone https://github.com/bojieli/verl.git chapter7/verl && git -C chapter7/verl checkout --detach 1593fc3a8cf894debdc3dece2a23ed739c282789  # 实验 7-14 ReTool 配方;7-15 训练后端
git clone https://github.com/bojieli/SandboxFusion.git chapter7/SandboxFusion && git -C chapter7/SandboxFusion fetch origin 4a0d573ebd64c98234c190a9d1d49e4276199a0c && git -C chapter7/SandboxFusion checkout --detach 4a0d573ebd64c98234c190a9d1d49e4276199a0c && test "$(git -C chapter7/SandboxFusion rev-parse HEAD)" = "4a0d573ebd64c98234c190a9d1d49e4276199a0c"  # 实验 7-14 代码沙箱
git clone https://github.com/thinking-machines-lab/tinker-cookbook.git chapter7/tinker-cookbook && git -C chapter7/tinker-cookbook checkout --detach fc8449187041cf102905f3f751e6d2eac7f9f754
git clone https://github.com/19PINE-AI/rlvp.git chapter7/RLVP/rlvp && git -C chapter7/RLVP/rlvp fetch origin 1ad30bc7e338911fb733739393d92c420f4d8bee && git -C chapter7/RLVP/rlvp checkout --detach 1ad30bc7e338911fb733739393d92c420f4d8bee && test "$(git -C chapter7/RLVP/rlvp rev-parse HEAD)" = "1ad30bc7e338911fb733739393d92c420f4d8bee"  # 实验 7-16
git clone https://github.com/PRIME-RL/SimpleVLA-RL.git chapter7/SimpleVLA-RL/SimpleVLA-RL && git -C chapter7/SimpleVLA-RL/SimpleVLA-RL checkout --detach 7c51662df27b586f9e8a1ab35fcf849f2b8852f9  # 实验 7-13

# 第 9 章 · GUI 与机器人外部复现轨道
git clone https://github.com/anthropics/claude-quickstarts.git chapter9/claude-quickstarts && git -C chapter9/claude-quickstarts checkout --detach 9bcc95e316e5ef6542b4c9d0469f4078829eead5  # 实验 9-6 使用 computer-use-demo/
git clone https://github.com/browser-use/browser-use.git chapter9/browser-use && git -C chapter9/browser-use checkout --detach ec9277c5001f2cb78ee419c927775a3cfc227ff8  # 实验 9-7
git clone https://github.com/Vector-Wangel/XLeRobot.git chapter9/XLeRobot && git -C chapter9/XLeRobot fetch origin 3d14695e40c9c68229c0aacffca6053c75cd3eb6 && git -C chapter9/XLeRobot checkout --detach 3d14695e40c9c68229c0aacffca6053c75cd3eb6 && test "$(git -C chapter9/XLeRobot rev-parse HEAD)" = "3d14695e40c9c68229c0aacffca6053c75cd3eb6"  # 实验 9-8、9-9 共用
git clone https://github.com/Grigorij-Dudnik/RoboCrew.git chapter9/RoboCrew && git -C chapter9/RoboCrew fetch origin c749148f29bd14e61347f9fc3530c343fff0d994 && git -C chapter9/RoboCrew checkout --detach c749148f29bd14e61347f9fc3530c343fff0d994 && test "$(git -C chapter9/RoboCrew rev-parse HEAD)" = "c749148f29bd14e61347f9fc3530c343fff0d994"  # 实验 9-9;RoboCrew v0.3.1
git clone https://github.com/StoneT2000/lerobot-sim2real.git chapter9/lerobot-sim2real && git -C chapter9/lerobot-sim2real fetch origin 87d6c1d969f6e0ca4dc5697940804e231118a63a && git -C chapter9/lerobot-sim2real checkout --detach 87d6c1d969f6e0ca4dc5697940804e231118a63a && test "$(git -C chapter9/lerobot-sim2real rev-parse HEAD)" = "87d6c1d969f6e0ca4dc5697940804e231118a63a"  # 实验 9-10

# 第 10 章 · 双 Agent 架构(已独立为 TalkAct 项目)+ 斯坦福 AI 小镇
git clone https://github.com/19PINE-AI/TalkAct.git chapter10/use-computer-while-calling && git -C chapter10/use-computer-while-calling fetch origin 7d70007f72d45ddfc1a14e8e229b6d444e4919a2 && git -C chapter10/use-computer-while-calling checkout --detach 7d70007f72d45ddfc1a14e8e229b6d444e4919a2 && test "$(git -C chapter10/use-computer-while-calling rev-parse HEAD)" = "7d70007f72d45ddfc1a14e8e229b6d444e4919a2"  # 实验 10-4
git clone https://github.com/joonspk-research/generative_agents.git chapter10/generative_agents && git -C chapter10/generative_agents fetch origin fe05a71d3e4ed7d10bf68aa4eda6dd995ec070f4 && git -C chapter10/generative_agents checkout --detach fe05a71d3e4ed7d10bf68aa4eda6dd995ec070f4 && test "$(git -C chapter10/generative_agents rev-parse HEAD)" = "fe05a71d3e4ed7d10bf68aa4eda6dd995ec070f4"  # 实验 10-7

上述九个当前缺失的 checkout(7-3、7-4、7-16、7-14 的 SandboxFusion、9-8/9-9 共用的 XLeRobot、9-9 的 RoboCrew、9-10 的 lerobot-sim2real、10-4、10-7)也已固定到不可变 SHA;命令会 detached checkout 并用 rev-parse HEAD 做相等性校验。第 10 章 use-computer-while-calling 已发展为独立维护的 19PINE-AI/TalkAct。源码存在或安装成功都不是实验完成声明。

🤝 贡献

本书与配套代码全部开源,非常欢迎社区通过 Pull Request 参与共建:

类型 说明
📝 书籍内容改进 勘误、补充、更清晰的表述,或新增前沿进展(正文见 book/chapter*.md
🐛 代码改进与 Bug 修复 让配套项目更健壮、更易用、更贴近生产实践
🧪 新的实践项目 为某个实验补充/替换更好的实现,或贡献全新的示例项目
🎨 配图设计改进 直接改进 book/images/ 中已签入的 SVG 图表,让它们更清晰美观
🌐 新语言翻译 欢迎翻译成更多语言,可参考英文(book-en/)、阿拉伯语(book-ar/)、繁體中文(台灣)版(book-zhtw/)、俄语(book-ru/)、泰米尔语(book-ta/)、越南语(book-vi/)、日语(book-ja/)、土耳其语(book-tr/)、韩语(book-ko/)、匈牙利语(book-hu/)的组织方式

提交前建议先把相关实验亲手跑一遍、确认可复现;也欢迎先提 issue 讨论想法。

📄 许可证

本项目采用 Apache License 2.0 开源许可证,详见 LICENSE 文件。部分子项目可能包含各自的许可证信息,请以子项目中的说明为准。

⭐ Star History

Star History Chart

scripts/gen_star_history.py 生成,GitHub Actions 每日自动更新 · 点击图片查看实时数据

View on GitHub

Recent activity

commits and pull requests

Recent open issues

view all

Releases and announcements

1 total
  1. Latest build (rolling)latestJul 21, 2026pre-release673 downloads

    Always-fresh PDF and EPUB builds from the latest `main` branch, rebuilt automatically on every book-content change. Assets are overwritten in place, so these download URLs are stable. - 简体中文: [PDF](https://github.com/bojieli/ai-agent-book/releases/download/latest/AI-Agents-in-Depth-zh-CN.pdf) · [EPUB](https://github.com/bojieli/ai-agent-book/releases/download/latest/AI-Agents-in-Depth-zh-CN.epub) - 繁體中文(台灣): [PDF](https://github.com/bojieli/ai-agent-book/releases/download/latest/AI-Agents-in-Depth-zh-TW.pdf) · [EPUB](https://github.com/bojieli/ai-agent-book/releases/download/latest/AI-Agents-in-Depth-zh-TW.epub) - English: [PDF](https://github.com/bojieli/ai-agent-book/releases/download/latest/AI-Agents-in-Depth-en.pdf) · [EPUB](https://github.com/bojieli/ai-agent-book/releases/download/latest/AI-Agents-in-Depth-en.epub) - Español: [PDF](https://github.com/bojieli/ai-agent-book/releases/download/latest/AI-Agents-in-Depth-es.pdf) · [EPUB](https://github.com/bojieli/ai-agent-book/releases/download/latest/AI-Agents-in-Depth-es.epub) - Bahasa Indonesia: [PDF](https://github.com/bojieli/ai-agent-book/releases/download/latest/AI-Agents-in-Depth-id.pdf) · [EPUB](https://github.com/bojiel

Commits per week

last 52 weeks
5040Week of 2025-08-10: 0 commitsWeek of 2025-08-17: 0 commitsWeek of 2025-08-24: 0 commitsWeek of 2025-08-31: 0 commitsWeek of 2025-09-07: 11 commitsWeek of 2025-09-14: 21 commitsWeek of 2025-09-21: 28 commitsWeek of 2025-09-28: 33 commitsWeek of 2025-10-05: 16 commitsWeek of 2025-10-12: 4 commitsWeek of 2025-10-19: 1 commitsWeek of 2025-10-26: 7 commitsWeek of 2025-11-02: 0 commitsWeek of 2025-11-09: 2 commitsWeek of 2025-11-16: 0 commitsWeek of 2025-11-23: 0 commitsWeek of 2025-11-30: 0 commitsWeek of 2025-12-07: 0 commitsWeek of 2025-12-14: 1 commitsWeek of 2025-12-21: 0 commitsWeek of 2025-12-28: 0 commitsWeek of 2026-01-04: 0 commitsWeek of 2026-01-11: 0 commitsWeek of 2026-01-18: 0 commitsWeek of 2026-01-25: 0 commitsWeek of 2026-02-01: 0 commitsWeek of 2026-02-08: 0 commitsWeek of 2026-02-15: 0 commitsWeek of 2026-02-22: 0 commitsWeek of 2026-03-01: 0 commitsWeek of 2026-03-08: 0 commitsWeek of 2026-03-15: 0 commitsWeek of 2026-03-22: 0 commitsWeek of 2026-03-29: 0 commitsWeek of 2026-04-05: 0 commitsWeek of 2026-04-12: 0 commitsWeek of 2026-04-19: 0 commitsWeek of 2026-04-26: 0 commitsWeek of 2026-05-03: 0 commitsWeek of 2026-05-10: 0 commitsWeek of 2026-05-17: 0 commitsWeek of 2026-05-24: 0 commitsWeek of 2026-05-31: 0 commitsWeek of 2026-06-07: 0 commitsWeek of 2026-06-14: 0 commitsWeek of 2026-06-21: 0 commitsWeek of 2026-06-28: 0 commitsWeek of 2026-07-05: 0 commitsWeek of 2026-07-12: 129 commitsWeek of 2026-07-19: 504 commitsWeek of 2026-07-26: 332 commitsWeek of 2026-08-02: 107 commitsAug 10, 2025Aug 2, 2026
1.2K commits in the last 52 weeks.

When work happens

weekday and hour
SunMonTueWedThuFriSat036912151821Sun 0:00 — 1 commitsSun 1:00 — 4 commitsSun 2:00 — 1 commitsSun 3:00 — 0 commitsSun 4:00 — 2 commitsSun 5:00 — 0 commitsSun 6:00 — 0 commitsSun 7:00 — 0 commitsSun 8:00 — 0 commitsSun 9:00 — 1 commitsSun 10:00 — 1 commitsSun 11:00 — 6 commitsSun 12:00 — 7 commitsSun 13:00 — 6 commitsSun 14:00 — 2 commitsSun 15:00 — 6 commitsSun 16:00 — 5 commitsSun 17:00 — 2 commitsSun 18:00 — 2 commitsSun 19:00 — 19 commitsSun 20:00 — 8 commitsSun 21:00 — 10 commitsSun 22:00 — 7 commitsSun 23:00 — 6 commitsMon 0:00 — 1 commitsMon 1:00 — 8 commitsMon 2:00 — 8 commitsMon 3:00 — 0 commitsMon 4:00 — 2 commitsMon 5:00 — 3 commitsMon 6:00 — 0 commitsMon 7:00 — 2 commitsMon 8:00 — 6 commitsMon 9:00 — 2 commitsMon 10:00 — 12 commitsMon 11:00 — 3 commitsMon 12:00 — 4 commitsMon 13:00 — 5 commitsMon 14:00 — 2 commitsMon 15:00 — 2 commitsMon 16:00 — 10 commitsMon 17:00 — 15 commitsMon 18:00 — 4 commitsMon 19:00 — 0 commitsMon 20:00 — 4 commitsMon 21:00 — 9 commitsMon 22:00 — 8 commitsMon 23:00 — 0 commitsTue 0:00 — 0 commitsTue 1:00 — 2 commitsTue 2:00 — 0 commitsTue 3:00 — 0 commitsTue 4:00 — 5 commitsTue 5:00 — 5 commitsTue 6:00 — 0 commitsTue 7:00 — 0 commitsTue 8:00 — 3 commitsTue 9:00 — 5 commitsTue 10:00 — 34 commitsTue 11:00 — 15 commitsTue 12:00 — 11 commitsTue 13:00 — 9 commitsTue 14:00 — 18 commitsTue 15:00 — 3 commitsTue 16:00 — 7 commitsTue 17:00 — 6 commitsTue 18:00 — 3 commitsTue 19:00 — 7 commitsTue 20:00 — 35 commitsTue 21:00 — 11 commitsTue 22:00 — 16 commitsTue 23:00 — 9 commitsWed 0:00 — 11 commitsWed 1:00 — 29 commitsWed 2:00 — 1 commitsWed 3:00 — 33 commitsWed 4:00 — 11 commitsWed 5:00 — 1 commitsWed 6:00 — 0 commitsWed 7:00 — 0 commitsWed 8:00 — 0 commitsWed 9:00 — 7 commitsWed 10:00 — 20 commitsWed 11:00 — 12 commitsWed 12:00 — 3 commitsWed 13:00 — 14 commitsWed 14:00 — 1 commitsWed 15:00 — 0 commitsWed 16:00 — 7 commitsWed 17:00 — 13 commitsWed 18:00 — 30 commitsWed 19:00 — 13 commitsWed 20:00 — 10 commitsWed 21:00 — 17 commitsWed 22:00 — 19 commitsWed 23:00 — 8 commitsThu 0:00 — 4 commitsThu 1:00 — 8 commitsThu 2:00 — 31 commitsThu 3:00 — 1 commitsThu 4:00 — 3 commitsThu 5:00 — 3 commitsThu 6:00 — 1 commitsThu 7:00 — 5 commitsThu 8:00 — 1 commitsThu 9:00 — 21 commitsThu 10:00 — 8 commitsThu 11:00 — 12 commitsThu 12:00 — 11 commitsThu 13:00 — 12 commitsThu 14:00 — 3 commitsThu 15:00 — 3 commitsThu 16:00 — 4 commitsThu 17:00 — 8 commitsThu 18:00 — 14 commitsThu 19:00 — 9 commitsThu 20:00 — 4 commitsThu 21:00 — 17 commitsThu 22:00 — 11 commitsThu 23:00 — 14 commitsFri 0:00 — 3 commitsFri 1:00 — 1 commitsFri 2:00 — 5 commitsFri 3:00 — 18 commitsFri 4:00 — 2 commitsFri 5:00 — 2 commitsFri 6:00 — 1 commitsFri 7:00 — 0 commitsFri 8:00 — 2 commitsFri 9:00 — 17 commitsFri 10:00 — 14 commitsFri 11:00 — 10 commitsFri 12:00 — 8 commitsFri 13:00 — 12 commitsFri 14:00 — 2 commitsFri 15:00 — 4 commitsFri 16:00 — 2 commitsFri 17:00 — 4 commitsFri 18:00 — 11 commitsFri 19:00 — 2 commitsFri 20:00 — 4 commitsFri 21:00 — 5 commitsFri 22:00 — 25 commitsFri 23:00 — 14 commitsSat 0:00 — 7 commitsSat 1:00 — 1 commitsSat 2:00 — 4 commitsSat 3:00 — 0 commitsSat 4:00 — 6 commitsSat 5:00 — 0 commitsSat 6:00 — 0 commitsSat 7:00 — 0 commitsSat 8:00 — 15 commitsSat 9:00 — 16 commitsSat 10:00 — 11 commitsSat 11:00 — 17 commitsSat 12:00 — 4 commitsSat 13:00 — 22 commitsSat 14:00 — 14 commitsSat 15:00 — 3 commitsSat 16:00 — 4 commitsSat 17:00 — 3 commitsSat 18:00 — 1 commitsSat 19:00 — 2 commitsSat 20:00 — 2 commitsSat 21:00 — 10 commitsSat 22:00 — 4 commitsSat 23:00 — 6 commits
Commit volume by weekday and hour (UTC). Larger dots mean more commits.

Who is committing

last 52 weeks
Maintainer commits726 (52%)
Community commits667 (48%)

1,393 commits in total over the last year.

DateListRankStars gained
Aug 2, 2026weekly#5+9,454
Aug 1, 2026weekly#5+9,454
Jul 31, 2026weekly#5+8,998
Jul 30, 2026weekly#5+8,998
Jul 29, 2026weekly#3+10,637
Jul 28, 2026weekly#3+13,627
Jul 27, 2026weekly#1+15,909
Jul 26, 2026daily#2+7
Jul 23, 2026daily#9+6
Jul 22, 2026daily#2+13
Jul 21, 2026daily#1+11
Jul 20, 2026daily#1+11
Jul 19, 2026daily#2+10
Jul 18, 2026daily#3+7
Jul 17, 2026daily#25+4
  • public-apis/public-apis

    A collective list of free APIs

    454.9K stars · Python

  • donnemartin/system-design-primer

    Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.

    362.2K stars · Python

  • practical-tutorials/project-based-learning

    Curated list of project-based tutorials

    277.1K stars · Python

  • affaan-m/ECC

    The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

    238.5K stars · JavaScript

  • affaan-m/ECC

    The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

    234.7K stars · JavaScript

  • NousResearch/hermes-agent

    The agent that grows with you

    227K stars · Python