LangGraph · Type Alias
Checkpoint
LangGraph checkpointers save graph state after each super-step. They use thread_id to organize checkpoints, enabling memory, human approval flows, replay, time travel, and recovery after failures.
Last updated
Syntax
graph = workflow.compile(checkpointer=checkpointer)
graph.invoke(input, {"configurable": {"thread_id": "1"}})In-depth API docs are only for subscribers: parameters, examples, common mistakes and interview practice.
SubscribeRelated
StateSnapshotget_stateget_state_historyupdate_stateInMemorySaverPostgresSaverSqliteSavercheckpoint_id