langgraph-checkpoint

Library with base interfaces for LangGraph checkpoint savers.

langgraph-checkpoint Permissive license MIT Active ★ 39,627 v4.2.0 released 2026-08-07

Install

langgraph-checkpoint on PyPI

pip

pip install langgraph-checkpoint

uv

uv add langgraph-checkpoint

poetry

poetry add langgraph-checkpoint

Package facts

License	MIT (permissive)
Python support	supports the current Python release (>=3.10)
Install friction	low — pure-Python wheel
Runtime dependencies	2 — langchain-core, ormsgpack
Maintenance	actively maintained — 6 days since the last release
Last repo commit	2026-08-12
First released	2024-08-02
Popularity	one of the top 1,000 most-downloaded packages on PyPI (30-day window, as of 2026-08-13)
Known vulnerabilities	none known (OSV.dev, checked 2026-08-13)

Evidence: langgraph_checkpoint-4.2.0-py3-none-any.whl

About langgraph-checkpoint

from the package's own PyPI description — quoted content, verbatim

LangGraph Checkpoint

PyPI - Version (image) PyPI - License (image) PyPI - Downloads (image) Twitter (image)

To help you ship LangGraph apps to production faster, check out LangSmith. LangSmith is a unified developer platform for building, testing, and monitoring LLM applications.

Quick Install

uv add langgraph-checkpoint

🤔 What is this?

This library defines the base interface for LangGraph checkpointers. Checkpointers provide a persistence layer for LangGraph: they save graph state at every superstep, enabling human-in-the-loop, memory between interactions, durable execution, and more.

📖 Documentation

For full documentation, see the...

Read as markdown · JSON record · Source repository

AI interpretation — verify before relying

AI-generated interpretation of the package facts above; every digit, version, license, or vulnerability id it cites is grounded in the facts already shown on this page

Defines the base interface and serialization protocol for LangGraph checkpointers, which persist graph state at every step to enable human-in-the-loop workflows, memory between interactions, and durable execution.

Low friction installation with just two runtime dependencies (langchain-core and ormsgpack). The package is actively maintained with a recent release and strong upstream project backing.

MIT license permits commercial and private use with minimal restrictions, making it suitable for production deployments.

Usage

from langgraph.checkpoint.memory import InMemorySaver

checkpointer = InMemorySaver()
config = {"configurable": {"thread_id": "1"}}
checkpointer.put(config, checkpoint_data, {}, {})
result = checkpointer.get(config)

Requires Python 3.10 or later. For security, set LANGGRAPH_STRICT_MSGPACK=true environment variable or pass allowed_msgpack_modules to JsonPlusSerializer to restrict deserialization to known-safe types.

Verdict: A lightweight, actively maintained library providing the checkpoint interface layer for LangGraph. MIT-licensed and low-friction to install, it's suitable for production use but requires explicit security configuration for checkpoint deserialization to prevent arbitrary code execution.

Needs verification

Whether InMemorySaver is the only built-in implementation or if other checkpoint backends are included in this package
Performance characteristics and scalability limits for checkpoint storage and retrieval operations
Whether the package includes migration utilities for upgrading checkpoint formats between versions

langgraph checkpoint persistencegraph state serializationlanggraph memory layercheckpoint saver interfacedurable graph executionlanggraph thread managementgraph state snapshots