Install & Compatibility
Where this runs
tested against v4.2.0 · pip install
no network on importno background threads
Install × environment matrix
Each cell = how many times install + import succeeded across repeated harness runs. Partial = flaky.
glibc = Debian/Ubuntu slim · musl = Alpine Linux
muslpy 3.10–3.95 runs
installs and imports cleanly · install 0.0s · import 1.188s · 70.3MB
glibcpy 3.10–3.95 runs
installs and imports cleanly · install 7.5s · import 1.116s · 78MB
73MB installed
● package 73MB
Code
Verified usage
Verified import paths — ran on the pinned version, not inferred.
BaseCheckpointSaver
✓ from langgraph.checkpoint.base import BaseCheckpointSaver
✗ from langgraph.checkpoint import BaseCheckpointSaver
Due to the transition to namespace packages, direct re-exported imports from `langgraph.checkpoint` are no longer supported since LangGraph v0.2 / langgraph-checkpoint v1.0.0.
InMemorySaver
✓ from langgraph.checkpoint.memory import InMemorySaver
The in-memory saver is provided for development and testing.
JsonPlusSerializer
✓ from langgraph.checkpoint.serde.jsonplus import JsonPlusSerializer
The default serializer for checkpoint data, handling various Python types.
This quickstart demonstrates how to set up a basic `StateGraph` and configure it with the `InMemorySaver` from `langgraph-checkpoint`. The `InMemorySaver` is suitable for local development and testing, saving state in memory. For persistent storage, you would typically use an external checkpointer like `PostgresSaver` or `SqliteSaver` from their respective `langgraph-checkpoint-*` libraries.
import os
from typing_extensions import TypedDict
from langgraph.graph import StateGraph, START, END
from langgraph.checkpoint.memory import InMemorySaver
# Define the state for the graph
class AgentState(TypedDict):
messages: list[str]
# Define a simple node
def chat_node(state: AgentState) -> AgentState:
# In a real agent, this would involve LLM calls or tool execution
print(f"Processing: {state['messages'][-1]}")
new_message = f"Echo: {state['messages'][-1]}"
return {"messages": state["messages"] + [new_message]}
# Build the graph
builder = StateGraph(AgentState)
builder.add_node("echo_chat", chat_node)
builder.add_edge(START, "echo_chat")
builder.add_edge("echo_chat", END)
# Initialize the in-memory checkpointer
checkpointer = InMemorySaver()
# Compile the graph with the checkpointer
# A real LangGraph application would likely use a more complex graph and invoke it
# to test persistence.
# For this quickstart, we just demonstrate setup.
graph = builder.compile(checkpointer=checkpointer)
# Example of how you would invoke (not part of langgraph-checkpoint itself, but for context)
# config = {"configurable": {"thread_id": "1"}}
# inputs = {"messages": ["Hello LangGraph!"]}
# result = graph.invoke(inputs, config=config)
# print(result)
Debug
Known issues
breakingThe `thread_ts` parameter was renamed to `checkpoint_id` in `langgraph-checkpoint` v1.0.0. While `thread_ts` is currently still recognized, it's deprecated. Update your code to use `checkpoint_id` for clarity and future compatibility.fixReplace `thread_ts` with `checkpoint_id` in your graph configuration (e.g., `{"configurable": {"thread_id": "1", "checkpoint_id": "some_uuid"}}`). affects: >=1.0.0
breakingDue to the move to namespace packages, direct imports from top-level `langgraph` modules (e.g., `langgraph.checkpoint`, `langgraph.graph`) are no longer valid. You must use the fully qualified path for the specific sub-module.fixChange import statements from `from langgraph.module import Symbol` to `from langgraph.module.submodule import Symbol` (e.g., `from langgraph.checkpoint.base import BaseCheckpointSaver`, `from langgraph.graph.state import StateGraph`).
affects: >=1.0.0
gotchaWhen using any checkpointer, `thread_id` is a mandatory configuration parameter for graph invocations to enable state persistence. Without it, the checkpointer cannot save or retrieve state.fixAlways include `{"configurable": {"thread_id": "your_unique_thread_id"}}` in your `graph.invoke()` or `graph.stream()` calls. affects: All versions
gotchaFor database-backed checkpointers (e.g., SQLite, PostgreSQL, MySQL), the `.setup()` method must be called on the checkpointer instance to create necessary tables before first use.fixEnsure you call `checkpointer.setup()` (or `await checkpointer.asetup()` for async) after initializing a database checkpointer.
affects: All versions of database checkpointer implementations
gotchaIn `langgraph-checkpoint-postgres` versions 2.0.22 and higher, metadata serialization changed. Non-JSON serializable objects (e.g., `HumanMessage` instances directly) stored in checkpoint metadata will now raise errors, as metadata is passed as JSONB.fixEnsure that any objects stored in checkpoint metadata are JSON serializable. Convert complex Python objects to their JSON-compatible representations before storing them, or move non-JSON data to dedicated channel blobs.
affects: langgraph-checkpoint-postgres >= 2.0.22
breakingSecurity vulnerabilities (CVE-2026-28277 for unsafe msgpack deserialization and CVE-2026-27022 for Redis query injection) have been disclosed impacting LangGraph's checkpoint system for certain backend implementations. These can lead to remote code execution or query injection.fixImmediately update to the latest versions of `langgraph-checkpoint` and any specific `langgraph-checkpoint-*` backend libraries you are using. Review your usage of community-contributed checkpointers for similar vulnerabilities.
affects: Specific backend implementations (e.g., `@langchain/langgraph-checkpoint-redis` prior to 1.0.2) and potentially others using msgpack serialization.
Errors
Common errors & fixes
ModuleNotFoundError: No module named 'langgraph.checkpoint.sqlite'
Specific checkpointer implementations like `SqliteSaver` or `PostgresSaver` are not part of the base `langgraph-checkpoint` library but are provided by separate, optional packages (`langgraph-checkpoint-sqlite` or `langgraph-checkpoint-postgres`) which need to be installed explicitly.
fixInstall the required package, for example: `pip install langgraph-checkpoint-sqlite` or `pip install langgraph-checkpoint-postgres`.
MISSING_CHECKPOINTER
The LangGraph application attempts to use persistence functionality (e.g., saving state) but no checkpointer instance has been provided to the graph's `compile()` method or `@entrypoint` decorator.
fixInstantiate a `BaseCheckpointSaver` (e.g., `InMemorySaver` for development or a production-grade saver like `PostgresSaver`) and pass it to the `compile()` method: `checkpointer = InMemorySaver()` `graph = builder.compile(checkpointer=checkpointer)`.
AttributeError: '_GeneratorContextManager' object has no attribute 'get_next_version'
When using `PostgresSaver.from_conn_string()` (or similar `from_conn_string` methods), it returns a context manager, not the `PostgresSaver` instance itself. Attempting to call methods like `setup()` directly on this context manager will result in an `AttributeError` or `TypeError`.
fixProperly use the context manager with a `with` statement to obtain the actual `PostgresSaver` instance: `with PostgresSaver.from_conn_string(DB_URI) as checkpointer: checkpointer.setup() # Now setup() is called on the actual saver instance`.
"DocumentTooLarge" errors during checkpoint saves
This error typically occurs when using a checkpointer with a backend like MongoDB, which has a 16MB document size limit. Storing large amounts of data or binary objects directly in the graph state can quickly exceed this limit as a new checkpoint is saved at every super-step.
fixReduce the size of the application state saved to checkpoints, avoid storing large binary data directly in the state (instead, store references to external storage), or consider switching to a database backend like PostgreSQL which supports larger field sizes.
Upgrade
Version history
4.2.0latest on PyPI · released Aug 7, 2026
Audit
Dependencies
langgraphrequiredCore framework that utilizes these checkpoint interfaces.
langgraph-checkpoint-sqliteoptionalCommon persistent checkpointer for local workflows and demos.
langgraph-checkpoint-postgresoptionalRobust persistent checkpointer recommended for production environments.
langgraph-checkpoint-awsoptionalAWS-specific persistence solution with various backends.