langgraph-checkpoint-sqlite
Library with a SQLite implementation of LangGraph checkpoint saver.
Decision gist · record as of 2026-08-14
Yes. Active maintenance, low install friction, no known vulnerabilities, and MIT licensing make this a solid choice for LangGraph state persistence in development and small-to-medium deployments. Install it if you are building LangGraph applications and need local or lightweight checkpoint storage; skip it if you require distributed state management or are already using a dedicated database backend.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.10 or later.
- Set LANGGRAPH_STRICT_MSGPACK=true or pass allowed_msgpack_modules to prevent code execution if database is compromised.
- Low friction installation with three runtime dependencies.
License · maintenance · safety
MIT (permissive) — MIT license permits commercial and private use with minimal restrictions; suitable for production deployments.
last release 2026-07-30 (15 days) · last repo commit 2026-08-14 · 39,691 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 3,538,545 downloads/mo, #2,586 on PyPI
Alternatives
Verify before relying
from langgraph.checkpoint.sqlite import SqliteSaver
with SqliteSaver.from_conn_string(":memory:") as checkpointer:
checkpointer.put(config, checkpoint, {}, {})
checkpointer.get(config)- Performance characteristics under high-volume checkpoint writes or large state objects
- SQLite file size limits and practical scalability for production workloads
- Compatibility with concurrent access patterns beyond the documented async interface
What it is and what it does
This package implements LangGraph's checkpoint saver interface using SQLite as the backing store. It allows LangGraph applications to persist execution state—channel values, versions, and metadata—across runs, enabling features like resumable workflows and state recovery. The library supports both synchronous and asynchronous operations via aiosqlite, making it suitable for local development, testing, and lightweight deployments where a full database service is not available.
The package is part of the LangGraph ecosystem and integrates directly with LangGraph's state management layer. It handles serialization of checkpoint data and provides methods to store, retrieve, and list checkpoints keyed by thread ID and namespace. A critical security note in the documentation emphasizes setting LANGGRAPH_STRICT_MSGPACK=true or supplying an explicit allowed_msgpack_modules list to restrict deserialization to known-safe types, preventing arbitrary code execution if the database is compromised.
Use it for
- Local development and testing of LangGraph applications where persistent state is needed without external infrastructure
- Lightweight production deployments on single machines or containers where SQLite's file-based storage is sufficient
- Building resumable workflows that can recover from interruptions by reloading checkpoint state
- Async LLM applications requiring non-blocking checkpoint operations via AsyncSqliteSaver
- Multi-threaded graph execution with per-thread state isolation using configurable thread IDs
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes.
Active maintenance, low install friction, no known vulnerabilities, and MIT licensing make this a solid choice for LangGraph state persistence in development and small-to-medium deployments. Install it if you are building LangGraph applications and need local or lightweight checkpoint storage; skip it if you require distributed state management or are already using a dedicated database backend.
Install
langgraph-checkpoint-sqlite on PyPI
Before you install
Low friction installation with three runtime dependencies. Actively maintained; last commit 2026-08-14 with 39691 repository stars. Requires Python 3.10 or later.
Requires Python 3.10 or later. Set LANGGRAPH_STRICT_MSGPACK=true or pass allowed_msgpack_modules to prevent code execution if database is compromised.
License in practice
MIT license permits commercial and private use with minimal restrictions; suitable for production deployments.
Quickstart
from langgraph.checkpoint.sqlite import SqliteSaver
with SqliteSaver.from_conn_string(":memory:") as checkpointer:
checkpointer.put(config, checkpoint, {}, {})
checkpointer.get(config)Verify before relying
- Performance characteristics under high-volume checkpoint writes or large state objects
- SQLite file size limits and practical scalability for production workloads
- Compatibility with concurrent access patterns beyond the documented async interface
Package facts
| License | MIT permissive |
| Python support | Supports the current Python release >=3.10 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 3 packagesaiosqlitelanggraph-checkpointsqlite-vec |
| Maintenance | Actively maintained 15 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 3,538,545 / month, #2,586 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
Evidence: langgraph_checkpoint_sqlite-3.1.1-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “sqlite checkpoint storage”
- langgraph-checkpoint-sqliteProvides a SQLite-backed checkpoint saver for LangGraph, enabling…
- seba-sqliteProvides legacy SQLite storage backend for the Everest optimizer,…
- azure-eventhub-checkpointstoreblobProvides a checkpoint store implementation for Azure Event Hubs…
Give your agent the search over MCP, or paste the wish link into any chat.
More Database packages
psycopg2-binary is a PostgreSQL database adapter for Python that implements the DB API 2.0 specification, enabling Python applications to connect to and query PostgreSQL databases with thread-safe concurrent operations.
Python client library for connecting to and executing commands against Redis key-value stores, supporting both synchronous and asynchronous operations.
Install it if your application needs to interact with Redis; the only prerequisite is a running Redis server instance.
YDB Python SDK is the official client library for connecting to and querying YDB databases from Python applications.
Install it if you need to connect Python applications to YDB databases.
Connects Python applications to Snowflake data warehouses using the DB API 2.0 specification, enabling SQL queries, data transfers, and warehouse operations.
sqlparse tokenizes SQL text into a tree of statements, clauses, and expressions, and provides functions to split scripts, format queries, and inspect parsed tokens without validating dialect or syntax.
Install it if you need to manipulate, format, or analyze SQL text programmatically.
Provides base adapter protocols and shared functionality that database adapters use to integrate with dbt-core, handling connections, dialect translation, relation caching, and core interface management.
See also langgraph-checkpoint · langgraph-checkpoint-postgres · seba-sqlite · langgraph-checkpoint-mongodb · langgraph-checkpoint-redis · langgraph-checkpoint-aws · langgraph · langgraph-cli · langsmith-fetch · historydict