Code link: https://github.com/krishnaik06/Agentic-LanggraphCrash-course
LangGraph is built for developers who want to build powerful, adaptable AI agents. Developers choose LangGraph for:

Reliability and controllability. Steer agent actions with moderation checks and human-in-the-loop approvals. LangGraph persists context for long-running workflows, keeping your agents on course.
Low-level and extensible. Build custom agents with fully descriptive, low-level primitives free from rigid abstractions that limit customization. Design scalable multi-agent systems, with each agent serving a specific role tailored to your use case.
First-class streaming support. With token-by-token streaming and streaming of intermediate steps, LangGraph gives users clear visibility into agent reasoning and actions as they unfold in real time.
Learn LangGraph basics¶
To get acquainted with LangGraph's key concepts and features, complete the following LangGraph basics tutorials series:

Build a basic chatbot
Add tools
Add memory
Add human-in-the-loop controls
Customize state
Time travel

Timestamp:

00:00:00 Introduction And Agenda
00:03:37 Langgraph Projects Structure
00:11:15 Building Blocks Of LAnggraph
00:23:47 Building a Basic Chatbot
00:49:05 Building Chatbot With Tools
01:18:37 ReACT Agent Architecture
01:26:22 Adding Memory In Langgraph
01:35:00 Streaming In Langgraph
01:44:58 Human Feedback In the loop
01:52:42 MCP Server Scratch Implementation

YouTube

A comprehensive tutorial covering the fundamentals of building agentic AI applications using LangGraph. The course demonstrates how to create basic chatbots, integrate external tools like Tavily search, implement custom functions, and manage state across graph nodes. Key concepts include understanding nodes, edges, and state management in graph-based AI workflows, with practical examples of tool binding and LLM integration for creating production-ready conversational agents.

Agentic AI With Langgraph And MCP Crash Course-Part 1