@luochang212/dive-into-langgraphPublic

LangGraph guide for Claude Code skills

This repo teaches LangGraph 1.0 with a chapter-by-chapter notebook guide and a companion skill package. The notebooks cover state graphs, middleware, memory, MCP servers, supervisor patterns, RAG, web search, and a Gradio app example.

450 stars•57 forks•Jupyter Notebook•Updated 1mo ago

Who it's for

Builders who want a guided path to using LangGraph and LangChain in Claude Code.

What it delivers

You can build LangGraph agents with reusable guidance instead of piecing together the framework from scratch.

What it does

Numbered LangGraph notebooks

Fourteen notebooks walk through quickstart, state graphs, middleware, human-in-the-loop flows, memory, context, MCP, supervisor patterns, parallelization, RAG, web search, deep agents, a Gradio app, a

Claude Code skill package

`skills/dive-into-langgraph/SKILL.md` packages the tutorial as a reusable skill for Claude Code.

MCP server examples

`mcp_server/` includes weather and math MCP examples plus a supervisor config for connecting tools to LangGraph.

Runnable example app

`app/` contains a Gradio-based agent app with its own docs, config, tests, and Docker setup.

Supporting examples

`examples/` includes sample scripts for LangMem, RAG, router, store, and time travel workflows.

How to get it

1使用 npx 安装本 Skill (dive-into-langgraph)：
```
npx skills add luochang212/dive-into-langgraph
```
2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 是由 LangChain…
```
pip install -r requirements.txt
```
3langgraph-cli 提供了一个可快速启动的调试页面。
```
langgraph dev
```

README

Dive into LangGraph

中文 | English

📚 在线阅读地址

📖《LangGraph 1.0 完全指南》

从零开始，动手实现强大的智能体

📢 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 安装本 Skill，即可写出高质量的 LangChain 和 LangGraph 代码。详见：SKILL.md

使用 npx 安装本 Skill (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 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 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

pip install -r requirements.txt

依赖包列表

以下为 requirements.txt 中的依赖包清单：

pydantic
python-dotenv
rank-bm25
langchain[openai]
langchain-community
langchain-mcp-adapters
langchain-text-splitters
langgraph
langgraph-cli[inmem]
langgraph-supervisor
langgraph-checkpoint-sqlite
langgraph-checkpoint-redis
langmem
ipynbname
fastmcp
bs4
scikit-learn
supervisor
jieba
dashscope
tavily-python
ddgs
deepagents

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	创建你的第一个 ReAct Agent
2	状态图	使用 StateGraph 创建工作流
3	中间件	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	使用内置的 HITL 中间件实现人机交互
5	记忆	创建短期记忆、长期记忆
6	上下文工程	使用 State、Store、Runtime 管理上下文
7	MCP Server	创建 MCP Server 并接入 LangGraph
8	监督者模式	两种方法实现监督者模式：tool-calling、langgraph-supervisor
9	并行	如何实现并发：节点并发、`@task` 装饰器、Map-reduce、Sub-graphs
10	RAG	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	实现联网搜索：DashScope、Tavily 和 DDGS
12	Deep Agents	简单介绍 Deep Agents
13	Gradio APP	基于 Gradio 开发流式对话智能体应用
14	附录：调试页面	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。

langgraph dev

详见：附录

五、实战章节

第 13 章开源了一个基于 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。

gradio_app

详见：/app

六、延伸阅读

官方文档：

官方教程：

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

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 国际许可协议进行许可。

Files in the repo

Repository payload•36 top-level entries

.github— GitHub workflows and templates
app— 21 items
book— 2 items
docs— Documentation
examples— Worked examples
img— 9 items
mcp_server— 4 items
scripts— Helper scripts
skills— The skills, one folder each
.env.example— Environment variables to set
.gitignore
.ruff.toml
1.quickstart.ipynb— Quickstart chapter for a first ReAct agent.
10.rag.ipynb— RAG chapter.
11.web_search.ipynb
12.deep_agents.ipynb
13.gradio_app.ipynb
14.langgraph_cli.ipynb
2.stategraph.ipynb— StateGraph workflow chapter.
3.middleware.ipynb— Middleware chapter with budget, truncation, sensitive-word, and PII handling.
4.human_in_the_loop.ipynb— Human-in-the-loop chapter.
5.memory.ipynb— Short-term and long-term memory chapter.
6.context.ipynb— Context engineering chapter.
7.mcp_server.ipynb— MCP Server chapter.
8.supervisor.ipynb— Supervisor pattern chapter.
9.parallelization.ipynb— Parallel execution chapter.
AGENTS.md— Instructions for Codex and other agents
create_references.sh
langgraph.json
LICENSE— License
myst.yml
pyproject.toml— Python package: install with pip or uv
README.md— The README
requirements.txt— Python package: install with pip or uv
simple_agent.py
uv.lock

Discussion (0)

Ask about usage, or say what you built with it

No comments yet. Be the first to say what this is good for.

More skills

obra/

superpowers

obra/superpowersSkills

An agentic skills framework & software development methodology that works.

285k

1 add

Graphify-Labs/graphifySkills

Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.

117k

1 add

Vincentwei1021/

anything2explainer

Vincentwei1021/anything2explainerSkills

Topic in, narrated explainer video out. A Claude Code / Codex skill that turns any topic into a black-canvas motion-graphics explainer video with TTS voiceover, subtitles and a chapter progress bar. Chinese or English; every frame drawn in code with Remotion.

666

anthropics/skillsSkills

Public repository for Agent Skills

176k

career-ops-hq/career-opsSkills

Open-source AI job search: scan job portals, evaluate listings into a structured A-H report with a global 1-5 score, tailor your CV, track applications — runs locally in your AI coding CLI (Claude Code, Codex, OpenCode, Antigravity…)

71k

addyosmani/agent-skillsSkills

Production-grade engineering skills for AI coding agents.

93k