Loading repository data…
Loading repository data…
pguso / repository
Comprehensive LangGraph course in TypeScript. Build stateful AI agents, chatbots, ReAct agents, and RAG systems with 12 lessons and working examples.
A transparent discovery signal based on current public GitHub metadata.
This score does not audit code, security, maintainers, documentation quality, or suitability. Verify the repository and its current documentation before adoption.
A hands-on introduction to building AI agents with LangGraph. Learn the fundamentals and build progressively more complex applications.
LangGraph is a library for building stateful, multi-actor applications with LLMs. It extends LangChain with:
Think of LangGraph as a way to build AI applications that can reason, act, and remember - not just respond to single prompts.
Install dependencies:
npm install --legacy-peer-deps
Set up environment:
cp env_example .env
# Add your OPENAI_API_KEY to .env
Read the overview: Start with the Course Overview to understand the learning path.
Begin learning: Start with Lesson 0: Fundamentals and proceed sequentially.
Before starting this course, you should have:
node --version)No prior AI/ML experience required - We'll explain concepts as we go. If you can write TypeScript functions, you're ready for this course.
npm install --legacy-peer-deps
Note: The --legacy-peer-deps flag is required due to peer dependency conflicts between LangChain packages. This is safe and commonly needed for LangChain projects.
Copy the example environment file:
cp env_example .env
Add your OpenAI API key to .env:
OPENAI_API_KEY=your-api-key-here
Run a simple example to verify everything works:
npm run example -- hello-world
The course consists of 12 lessons, organized into three main sections that progressively build complexity:
Goal: Understand core concepts and build your first graphs
** Tip for beginners:** You can start with Lesson 1 to learn by doing, then come back to Lesson 0 for deeper understanding of the concepts.
Goal: Learn different graph patterns and control flow
Goal: Build real AI agents with increasing complexity
Each lesson includes:
Each lesson includes a working example. Run them using:
npm run example -- <example-name>
| Example Name | Description |
|---|---|
hello-world | Your first working graph |
multiple-inputs | Working with complex state structures |
sequential-graph | Multi-step workflows |
conditional-graph | Decision-making and branching |
looping-graph | Iterative processes and loops |
simple-bot | Basic chatbot with LLM integration |
chat-bot | Advanced conversation handling with memory |
tools | Giving your LLM access to functions |
react-agent | Reasoning and acting agents |
human-feedback-agent | Interactive agents with human approval |
rag-basic | Document retrieval and question-answering |
error-handling | Error handling, retries, and recovery patterns |
# Run the hello world example
npm run example -- hello-world
# Run the RAG example
npm run example -- rag-basic
langgraph-course/
├── examples/ # Working code examples for each lesson
├── lessons/ # Lesson markdown files with explanations
├── graphs/ # Visual graph representations
├── scripts/ # Utility scripts (e.g., run-example.ts)
├── utils/ # Helper utilities
├── pdfs/ # Sample PDFs for RAG examples
├── package.json # Project dependencies and scripts
├── tsconfig.json # TypeScript configuration
└── README.md # This file
Problem: npm install fails with peer dependency warnings
Solution: Use npm install --legacy-peer-deps as shown in the installation instructions.
Problem: TypeScript errors when running examples
Solution: Ensure you have TypeScript installed globally or run npm install to get dev dependencies.
Problem: OPENAI_API_KEY not found error
Solution:
.env file from env_example.envProblem: Example script not found
Solution: Ensure you're using the correct example name. Check the Available Examples table above.
Problem: Module not found errors
Solution: Run npm install --legacy-peer-deps again to ensure all dependencies are installed.