Back to search
dive-into-langgraph
SkillGitHub
LangGraph 1.0 Tutorial
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Checked today
Badge for your README
Markdown
[](/listings/luochang212--dive-into-langgraph)HTML
<a href="/listings/luochang212--dive-into-langgraph"><img src="/api/listings/luochang212--dive-into-langgraph/badge.svg" alt="findsafeskills safety rating" /></a>Install
i
What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
README.md · README · 168 lines
View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)
- <div align="center">
- <img src="./img/social-preview.webp" width="100%">
- <h1>Dive into LangGraph</h1>
- </div>
- <div align="center">
- <img src="https://img.shields.io/github/stars/luochang212/dive-into-langgraph?style=flat&logo=github" alt="GitHub stars"/>
- <img src="https://img.shields.io/github/forks/luochang212/dive-into-langgraph?style=flat&logo=github" alt="GitHub forks"/>
- <img src="https://img.shields.io/badge/language-Chinese-brightgreen?style=flat" alt="Language"/>
- <a href="https://github.com/luochang212/dive-into-langgraph/actions/workflows/ci.yml"><img src="https://github.com/luochang212/dive-into-langgraph/actions/workflows/ci.yml/badge.svg?branch=main" alt="ci"/></a>
- <a href="https://github.com/luochang212/dive-into-langgraph/actions/workflows/deploy-book.yml"><img src="https://github.com/luochang212/dive-into-langgraph/actions/workflows/deploy-book.yml/badge.svg?branch=main" alt="deploy-book"/></a>
- <a href="https://zread.ai/luochang212/dive-into-langgraph"><img src="https://img.shields.io/badge/%E2%80%8B-zread-00b0aa?style=flat&logo=data%3Aimage%2Fsvg%2Bxml%3Bbase64%2CPHN2ZyB3aWR0aD0iMTYiIGhlaWdodD0iMTYiIHZpZXdCb3g9IjAgMCAxNiAxNiIgZmlsbD0ibm9uZSIgeG1sbnM9Imh0dHA6Ly93d3cudzMub3JnLzIwMDAvc3ZnIj4KPHBhdGggZD0iTTQuOTYxNTYgMS42MDAxSDIuMjQxNTZDMS44ODgxIDEuNjAwMSAxLjYwMTU2IDEuODg2NjQgMS42MDE1NiAyLjI0MDFWNC45NjAxQzEuNjAxNTYgNS4zMTM1NiAxLjg4ODEgNS42MDAxIDIuMjQxNTYgNS42MDAxSDQuOTYxNTZDNS4zMTUwMiA1LjYwMDEgNS42MDE1NiA1LjMxMzU2IDUuNjAxNTYgNC45NjAxVjIuMjQwMUM1LjYwMTU2IDEuODg2NjQgNS4zMTUwMiAxLjYwMDEgNC45NjE1NiAxLjYwMDFaIiBmaWxsPSIjZmZmIi8%2BCjxwYXRoIGQ9Ik00Ljk2MTU2IDEwLjM5OTlIMi4yNDE1NkMxLjg4ODEgMTAuMzk5OSAxLjYwMTU2IDEwLjY4NjQgMS42MDE1NiAxMS4wMzk5VjEzLjc1OTlDMS42MDE1NiAxNC4xMTM0IDEuODg4MSAxNC4zOTk5IDIuMjQxNTYgMTQuMzk5OUg0Ljk2MTU2QzUuMzE1MDIgMTQuMzk5OSA1LjYwMTU2IDE0LjExMzQgNS42MDE1NiAxMy43NTk5VjExLjAzOTlDNS42MDE1NiAxMC42ODY0IDUuMzE1MDIgMTAuMzk5OSA0Ljk2MTU2IDEwLjM5OTlaIiBmaWxsPSIjZmZmIi8%2BCjxwYXRoIGQ9Ik0xMy43NTg0IDEuNjAwMUgxMS4wMzg0QzEwLjY4NSAxLjYwMDEgMTAuMzk4NCAxLjg4NjY0IDEwLjM5ODQgMi4yNDAxVjQuOTYwMUMxMC4zOTg0IDUuMzEzNTYgMTAuNjg1IDUuNjAwMSAxMS4wMzg0IDUuNjAwMUgxMy43NTg0QzE0LjExMTkgNS42MDAxIDE0LjM5ODQgNS4zMTM1NiAxNC4zOTg0IDQuOTYwMVYyLjI0MDFDMTQuMzk4NCAxLjg4NjY0IDE0LjExMTkgMS42MDAxIDEzLjc1ODQgMS42MDAxWiIgZmlsbD0iI2ZmZiIvPgo8cGF0aCBkPSJNNCAxMkwxMiA0TDQgMTJaIiBmaWxsPSIjZmZmIi8%2BCjxwYXRoIGQ9Ik00IDEyTDEyIDQiIHN0cm9rZT0iI2ZmZiIgc3Ryb2tlLXdpZHRoPSIxLjUiIHN0cm9rZS1saW5lY2FwPSJyb3VuZCIvPgo8L3N2Zz4K&logoColor=ffffff" alt="zread"/></a>
- </div>
- <div align="center">
- 中文 | [English](./docs/README-en.md)
- </div>
- <div align="center">
- <p><a href="https://luochang212.github.io/dive-into-langgraph/">📚 在线阅读地址</a></p>
- <h3>📖《LangGraph 1.0 完全指南》</h3>
- <p><em>从零开始,动手实现强大的智能体</em></p>
- </div>
- ---
- ## 📢 News
- ### ✨ 2026-03-02 更新
- 本教程已转为 Agent Skill。现在无需使用人脑学习本教程,只需要为你的 [Claude Code](https://github.com/anthropics/claude-code) 安装本 Skill,即可写出高质量的 LangChain 和 LangGraph 代码。详见:[SKILL.md](skills/dive-into-langgraph/SKILL.md)
- 使用 npx 安装本 Skill ([dive-into-langgraph](https://skills.sh/luochang212/dive-into-langgraph/dive-into-langgraph)):
- ```
- npx skills add luochang212/dive-into-langgraph
- ```
- ## 一、项目介绍
- > 2025 年 10 月中旬,LangGraph 发布 1.0 版本。开发团队承诺这是一个稳定版本,预计未来接口不会大改,因此现在正是学习它的好时机。
- 这是一个开源电子书项目,旨在帮助 Agent 开发者快速掌握 LangGraph 框架。[LangGraph](https://github.com/langchain-ai/langgraph) 是由 LangChain 团队开发的开源智能体框架。它功能强大,你要的记忆、MCP、护栏、状态管理、多智能体它全都有。LangGraph 通常与 [LangChain](https://github.com/langchain-ai/langchain) 一起使用:LangChain 提供基础组件和工具,LangGraph 负责工作流和状态管理。因此,两个库都需要学习。为了让大家快速入门,本教程将两个库的主要功能提取出来,分成 14 个章节进行介绍。
- ## 二、安装依赖
- ```bash
- uv sync
- ```
- <details>
- <summary>依赖包列表</summary>
- `pyproject.toml` 声明的主要依赖如下,精确版本以 `uv.lock` 为准:
- ```text
- pydantic
- python-dotenv
- rank-bm25
- langchain[mcp,openai]
- langchain-text-splitters
- langchain-tavily
- langgraph
- langgraph-cli[inmem]
- langgraph-checkpoint-sqlite
- langgraph-checkpoint-redis
- langmem
- ipynbname
- fastmcp
- bs4
- requests
- scikit-learn
- supervisor
- jieba
- ddgs
- deepagents
- ```
- </details>
- ### 代码质量与 Git Hook
- 首次克隆后安装仓库的 pre-commit Hook:
- ```bash
- uv run pre-commit install
- ```
- Hook 会在每次提交前检查全仓 Ruff 格式和 lint,但不会自动改写文件。手动执行同一套 CI 检查:
- ```bash
- uv run pre-commit run --all-files
- ```
- ## 三、章节目录
- 本教程的内容速览:
- | 序号 | 章节 | 主要内容 |
- | -- | -- | -- |
- | 1 | [快速入门](./1.quickstart.ipynb) | 创建你的第一个 ReAct Agent |
- | 2 | [状态图](./2.stategraph.ipynb) | 使用 StateGraph 创建工作流 |
- | 3 | [中间件](./3.middleware.ipynb) | 使用自定义中间件实现四个功能:预算控制、消息截断、敏感词过滤、PII 检测 |
- | 4 | [人机交互](./4.human_in_the_loop.ipynb) | 使用内置的 HITL 中间件实现人机交互 |
- | 5 | [记忆](./5.memory.ipynb) | 创建短期记忆、长期记忆 |
- | 6 | [上下文工程](./6.context.ipynb) | 使用 State、Store、Runtime 管理上下文 |
- | 7 | [MCP Server](./7.mcp_server.ipynb) | 创建 MCP Server 并接入 LangGraph |
- | 8 | [监督者模式](./8.supervisor.ipynb) | 使用官方推荐的 subagents-as-tools 模式实现监督者 |
- | 9 | [并行](./9.parallelization.ipynb) | 如何实现并发:节点并发、`@task` 装饰器、Map-reduce、Sub-graphs |
- | 10 | [RAG](./10.rag.ipynb) | 三种方式实现 RAG:向量检索、关键词检索、混合检索 |
- | 11 | [网络搜索](./11.web_search.ipynb) | 实现联网搜索:DashScope、Tavily、DDGS 和 Exa MCP |
- | 12 | [Deep Agents](./12.deep_agents.ipynb) | 简单介绍 Deep Agents |
- | 13 | [Gradio APP](./13.gradio_app.ipynb) | 基于 Gradio 开发流式对话智能体应用 |
- | 14 | [附录:调试页面](./14.langgraph_cli.ipynb) | 介绍 langgraph-cli 提供的调试页面 |
- > \[!NOTE\]
- >
- > **承诺**:本教程完全基于 LangGraph v1.0 编写,不含任何 v0.6 的历史残留。
- ## 四、调试页面
- `langgraph-cli` 提供了一个可快速启动的调试页面。
- ```bash
- langgraph dev
- ```
- 详见:[附录](https://luochang212.github.io/dive-into-langgraph/langgraph-cli/)
- ## 五、实战章节
- [第 13 章](https://luochang212.github.io/dive-into-langgraph/gradio-app/) 开源了一个基于 Gradio + LangChain 实现的智能体应用,效果如下。你可以为这个应用添加更多功能,定制专属于你的智能体。
- 
- 详见:[/app](./app/)
- ## 六、延伸阅读
- **官方文档:**
- - [LangChain](https://docs.langchain.com/oss/python/langchain/overview)
- - [LangGraph](https://docs.langchain.com/oss/python/langgraph/overview)
- - [Deep Agents](https://docs.langchain.com/oss/python/deepagents/overview)
- - [LangMem](https://langchain-ai.github.io/langmem/)
- **官方教程:**
- - [langgraph-101](https://github.com/langchain-ai/langgraph-101)
- - [langchain-academy](https://github.com/langchain-ai/langchain-academy)
- ## 七、如何贡献
- 我们欢迎任何形式的贡献!
- - 🐛 报告 Bug - 发现问题请提交 Issue
- - 💡 功能建议 - 有好想法就告诉我们
- - 📝 内容完善 - 帮助改进教程内容
- - 🔧 代码优化 - 提交 Pull Request
- ## 八、Star History
- [](https://www.star-history.com/#luochang212/dive-into-langgraph&type=date&legend=top-left)
- ## 九、开源协议
- 本作品采用 [知识共享署名-非商业性使用-相同方式共享 4.0 国际许可协议](http://creativecommons.org/licenses/by-nc-sa/4.0/) 进行许可。
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.