LangMem vs Memory (MCP reference server)

LangMem

Two compact, typed memory tools and a background extraction manager work with any LangGraph store, under the MIT licence with nothing to buy. The newest PyPI release, 0.0.30, dates from 27 October 2025. The repository has no changelog, tags or test workflow, and 23 of 54 open issues have no reply.

Memory (MCP reference server)

Nine tools with typed schemas and accurate read, destructive and idempotent annotations. No pagination or limits. read_graph returns everything and search_nodes every match.

LangMem

1. Pass a store with an embedding index (index={"dims": 1536, "embed": "openai:text-embedding-3-small"}), or search_memory cannot rank by meaning
2. Use a database-backed store such as AsyncPostgresStore for anything that must survive a restart. InMemoryStore loses everything
3. Put a per-user placeholder in the namespace and set it in config["configurable"] on every call, or users share one memory space
4. Send the memory id with update and delete, and never with create. A retried create writes a duplicate under a new UUID
5. Run on Python 3.11 or later. src/langmem/knowledge/extraction.py uses typing.NotRequired, which Python 3.10 lacks

Memory (MCP reference server)

1. Set MEMORY_FILE_PATH to an absolute path. The default sits inside the npx cache
2. Use search_nodes or open_nodes instead of read_graph once the graph has more than a few hundred entities
3. Make memory writes one at a time. Parallel calls in one turn can overwrite each other in 2026.8.31
4. Create both entities before create_relations. A missing endpoint fails the whole batch
5. Keep observations short and factual. They come back verbatim in every later read