State: the dictionary every node shares

The state is the one dictionary that travels between the nodes of a graph. Every node is handed it and returns the keys it wants to change.

Last updated: 27 Sep, 2026 · LangGraph 1.2

Before any graph, a node is only a function that takes a dictionary and returns a dictionary. Start there.

A node reading and returning state

Example

def greet(state):
    return {"greeting": "Hello!"}

print(greet({}))

Why the argument is called state

It takes one argument and returns a dictionary. Nothing clever yet. The argument is called state because in a graph one dictionary is passed from function to function, and that dictionary is the state.

Describing the shape with TypedDict

python

from typing_extensions import TypedDict

class State(TypedDict):
    ticket: str
    category: str

A TypedDict says which keys the state has and their types. It is the recommended shape: plain dictionary typing, no runtime cost. LangGraph also accepts a Pydantic model when you want values validated as they come in, at some speed cost.

TypedDict vs Pydantic for state

	TypedDict	Pydantic BaseModel
Validation	None at runtime	Validates values on input
Speed	Fastest	Slower
Use when	Most graphs	You want bad input caught early

When you declare a state

Every graph declares a state; it is the first thing you write.
Anything one node must pass to another goes in the state.

Watch out. The state is your program's memory. If a node works something out and does not return it, it is gone when the function ends.

Try it yourself

Add a reply key to State.
Make greet return two keys and print the result.

PreviousInstallation and setup

You understood something today that you didn't yesterday.

State: the dictionary every node shares

A node reading and returning state

Why the argument is called state

Describing the shape with TypedDict

TypedDict vs Pydantic for state

When you declare a state

Related