LangGraphLangGraph 1.2 · Python 3.10+
0%
1
Curious builder0 XP earned · 300 to level 2
0 daysFinish a lesson to begin
Badge collection0 of 6 unlocked
38 small wins to finish your pathNext lesson →

LangGraph logoLangGraph overview

LangGraph is LangChain's open-source framework for building AI agents as graphs: small Python functions that share one state dictionary and decide which step runs next.

Last updated: 27 Sep, 2026 · LangGraph 1.2 · Python 3.10+

It is developed by LangChain and released under the MIT licence. The docs describe it as a low-level orchestration framework for building and running long-running, stateful agents.

What LangGraph is for

LangGraph suits work that mixes fixed steps with decisions a model makes, and that needs pauses, retries or memory. LangChain provides chat models, message types and tools; LangGraph decides the order steps run in and keeps the state between them.

The agent you will build, and the lesson each piece comes from
graph · StateGraph(MessagesState)tools bound to the modelasksinvoke(messages)tool callresultansweredreplyruns the callsaves every stepinterruptresumeCustomerChat modelPretendModel + toolscall_modelnodetoolsToolNode(tools)ENDlookup_orderjust runsrefundasks firstYou, approvingCommand(resume)CheckpointerInMemorySaver
Hover or tap a piece to see what it is and which lesson built it.
Trace a request

Pick one to watch it run, step by step.

How it works

A LangGraph program is a set of Python functions, called nodes, that pass one dictionary, called the state, between them. You write the functions and say which one runs after which; LangGraph runs them and carries the state along.

Because the connections can point backwards, a program can repeat a step until the job is done. Plain sequential code needs extra loops and flags to do the same, and they grow hard to follow.

What you will build

A support agent that reads a message, decides what to do, looks things up with tools, remembers the conversation, and stops to ask before anything it cannot undo. Each lesson adds a few lines, runs them, and explains what changed.

Everything in this course, and where it is going
Setup and plain PythonMaking decisionsTalking to a modelMemoryControl and shapeA real model and the support agentBuild a documentation assistanta state, one dictionarynodes, ordinary functionsedges, what runs nextbranch on the stateloop until it is donerun two things at oncemessagestoolsthe agent loopone conversationkeeping it shortfacts about a personpause and ask a humanwatch it rungo back in timecreate_agenta real modelthe support agentretrievalgrounded answersrunning it as a server
Hover or tap a piece to see what it is and which lesson built it.

Where you use LangGraph

  • Multi-step assistants where a model decides the next action, not a fixed script.
  • Flows that branch, retry, or run steps in parallel.
  • Agents that pause for a human approval and resume later.
  • Anything that needs memory across turns or a run you can inspect and replay.

Advantages and limits

  • Advantage: the flow is explicit, so branches, loops and retries are visible and debuggable.
  • Advantage: state, memory, human approval and streaming are built in.
  • Advantage: uses LangChain's models and tools, so any provider LangChain integrates with is available.
  • Limit: for a single model call with no branching, a plain function is simpler.
  • Limit: you think in graphs, a small step over calling functions directly.

Prerequisites

  • Python functions and dictionaries.
  • No API key needed: lessons 2 to 6 are plain Python; a model arrives later.
  • Python 3.10 or newer.
Back toAll frameworks

Every expert started right here.