LangChain LangGraph
Open source and free · In-depth explanation in Chinese

AI Agent Foundation

Based on the official courses of LangChain Academy, each Jupyter Notebook is analyzed one by one, and the code logic and design principles are truly explained in Chinese - not translation, but analysis.

2 learning path
9 Core Modules
60+ handout page
100% Free and open source
📖
Content source
Based on the following two official LangChain Academy courses
This website explains each Jupyter Notebook of each Module in the two courses one by one in Chinese, analyzing the code logic and design principles to help learners truly understand, rather than just run through the code.

4 production-level practical projects

Each Module Summary has a built-in end-to-end practical project, which connects all the knowledge points of the Module into a complete, directly runnable real system.

LangGraph · Module 1 ✈️

Intelligent travel planning assistant

Travel Planning Agent

A travel planning assistant capable of multi-step reasoning, automatic tool calling, and cross-wheel memory of user preferences. All six core knowledge points of Module 1 are connected into a complete runnable project, covering the complete link from StateGraph construction to Studio deployment.

StateGraph MessagesState ToolNode ReAct loop MemorySaver Studio deployment
LangGraph · Module 2 🔬

Intelligent research assistant

AI Research Assistant

An intelligent assistant that supports multiple rounds of dialogue, automatic history compression, and cross-session persistent memory. Organically integrating all six core knowledge points of Module 2, it is a LangGraph project skeleton that can be directly used in the production environment.

Pydantic Schema add_messages Multiple Schemas trim_messages scrolling summary SQLite persistence
LangGraph · Module 3 📋

Smart Contract Approval Assistant

Smart Contract Approval Agent

A contract processing workflow that integrates streaming progress display, manual approval, status editing, dynamic risk interruption and historical review. Integrate all 5 core knowledge points of Module 3 to simulate real enterprise-level approval scenarios.

Streaming Breakpoints update_state interrupt() Time Travel
LangGraph · Module 5 🧠

personal study companion

Personal Learning Companion Agent

A learning assistant that can continue to understand you across multiple conversations - record knowledge background (Profile), accumulate study notes (Collection), and let LLM decide independently when to extract and retrieve memories (Memory Agent).

InMemoryStore Profile Schema Collection Schema Memory Agent Semantic retrieval

Why choose this course?

It's not a translation, it's an in-depth analysis - the design intent and code principles behind each Notebook will be completely dismantled.

🔍
Line-by-line code analysis
Each Jupyter Notebook has its own explanation page, where the code logic and design principles are analyzed one by one, rather than simply displaying the running results.
🗺️
clear learning path
First LangChain and then LangGraph, the path is clear and step-by-step to avoid knowledge gaps caused by jump learning.
Oriented to production practice
Covers all core capabilities required for building production-level Agents such as HITL, parallelism, long-term memory, and deployment.
📦
Official content guaranteed
Strictly based on the official courses of LangChain Academy, ensuring that the source of knowledge is authoritative and reliable and the content is accurate.

Recommended learning order

First establish awareness of the basic components of Agent, and then go deep into schema orchestration and production deployment. The two paths are connected one after the other, and both are indispensable.

Step 1 · Learn first
🔗
LangChain
3 Modules · Agent basic capabilities

Establish the basic capabilities of Agent application: model calling, prompt engineering, tool usage, MCP protocol, RAG knowledge retrieval, SQL query, middleware and manual approval process.

  • Models
  • Prompting
  • Tools
  • Memory
  • MCP
  • Multi-Agent
  • RAG
  • SQL
  • HITL
Step 2 · Learn later
🕸️
LangGraph
6 Modules · Schematic orchestration and production deployment

Continue to learn graph orchestration based on LangChain: StateGraph, state management, Human-in-the-Loop intervention, parallel execution, cross-session long-term memory and production environment deployment.

  • StateGraph
  • State
  • Memory
  • HITL
  • Parallelization
  • Subgraph
  • Map-Reduce
  • Deployment

Complete list of 9 Modules

Click on any module card to jump directly and quickly locate the content you need.

💡

Suggested learning paths:LangChain is responsible for understanding the basic components of Agent - model invocation, tool usage, memory management, and multi-Agent collaboration. On this basis, LangGraph teaches you to organize these components into complex workflows that are controllable, recoverable, and can run stably in a production environment.

What can you master after studying?

Covering the complete AI Agent development skills stack from basic components to production deployment, the green markers are from the LangChain path and the purple markers are from the LangGraph path.

Call and manage large language models
Design efficient Prompt templates
Build Tool-calling Agent
Integrated MCP protocol tools
Implement RAG knowledge retrieval
Agent operates relational database
Multi-Agent system collaborative orchestration
Human-in-the-Loop approval flow
Modeling workflows with StateGraph
Design status Schema and Reducer
Graph execution breakpoints and time travel
Parallel subgraphs and Map-Reduce
Cross-session long-term memory storage
Production-grade LangGraph deployment