LangGraph 1 cheatsheet

LangGraph 1: Memory and persistence

7 common LangGraph 1 tasks.

Add short-term memory

Compile with a checkpointer to save state after every step. Use InMemorySaver for experiments only.

from langgraph.checkpoint.memory import InMemorySaver

graph = builder.compile(checkpointer=InMemorySaver())

Continue a conversation on a thread

Calls that share a thread_id share state.

config = {"configurable": {"thread_id": "user-1"}}
graph.invoke(inputs, config)

Read the saved state

Get the latest state of a thread.

graph.get_state(config)

Browse state history

Iterate over past checkpoints of a thread, newest first. Useful for debugging and time travel.

for snapshot in graph.get_state_history(config):
    print(snapshot.values)

Persist to SQLite

Install the SQLite checkpointer. It keeps state across restarts for local use.

pip install -U langgraph-checkpoint-sqlite

Persist to PostgreSQL

Use PostgreSQL for production. Install the package, then create the tables once with setup().

pip install -U langgraph-checkpoint-postgres

from langgraph.checkpoint.postgres import PostgresSaver

with PostgresSaver.from_conn_string(DB_URI) as checkpointer:
    checkpointer.setup()

Add long-term memory

A store keeps data across threads, such as facts about a user.

from langgraph.store.memory import InMemoryStore

graph = builder.compile(checkpointer=InMemorySaver(), store=InMemoryStore())

Was this page helpful?