# LangMem vs Memory (MCP reference server)

> Memory scores 54.2 (C) to LangMem's 47.9 (D) for agent memory. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/langmem-vs-memory-reference-server
- Markdown: https://www.anchorterminal.com/compare/langmem-vs-memory-reference-server.md (~2,450 tokens)
- Slim: https://www.anchorterminal.com/compare/langmem-vs-memory-reference-server.min.md (~630 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/langmem-vs-memory-reference-server.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- Updated: 2026-10-08

Memory (MCP reference server) scores 54.2 (C) on agent readiness against LangMem's 47.9 (D), and leads in 5 of 7 scored categories. LangMem leads on security & auth. Both do agent memory.

- LangMem: grade D, 47.9/100, rank #826 of 950. Markdown https://www.anchorterminal.com/tools/langmem.md · JSON https://www.anchorterminal.com/api/v1/tools/langmem.json
- Memory (MCP reference server): grade C, 54.2/100, rank #690 of 950. Markdown https://www.anchorterminal.com/tools/memory-reference-server.md · JSON https://www.anchorterminal.com/api/v1/tools/memory-reference-server.json
- Best memory layers for AI agents: https://www.anchorterminal.com/best/agent-memory/index.md
- All 55 memory comparisons: https://www.anchorterminal.com/compare/agent-memory/index.md
- Best database, file and memory tools for AI agents: https://www.anchorterminal.com/best/data/index.md
- All 43 databases comparisons: https://www.anchorterminal.com/compare/data/index.md

## Which one, for what

### LangMem (D)

Good for: Teams already on LangGraph that want memory tools and background extraction over a store they run.

Ahead on:
- Security & auth, 45 against 32

Watch for: The newest PyPI release, 0.0.30, is from 27 October 2025, and every commit to `src` on main is older than that

### Memory (MCP reference server) (C)

Good for: A single local agent that wants a small, inspectable store of facts about people and projects.

Ahead on:
- Reliability, 52 against 32
- Schema & documentation, 60 against 55
- Maintenance & community, 43 against 15
- Transparency & trust, 72 against 59

Also in its favour:
- Runs on your own machine

Watch for: No pagination or limits. `read_graph` returns everything and `search_nodes` every match


## Score by category

| Category | Weight | LangMem | Memory (MCP reference server) | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 32 | 52 | Memory (MCP reference server) +20 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 55 | 60 | Memory (MCP reference server) +5 |
| Agent ergonomics | 13% (16.2 this run) | 66 | 67 | Memory (MCP reference server) +1 |
| Security & auth | 14% (17.5 this run) | 45 | 32 | LangMem +13 |
| Payments & pricing | 10% (12.5 this run) | 60 | 60 | even |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 15 | 43 | Memory (MCP reference server) +28 |
| Transparency & trust | 7% (8.8 this run) | 59 | 72 | Memory (MCP reference server) +13 |
| Negative events | ≤15 | 0 | 0 | |
| **Total** | | **47.9 · D** | **54.2 · C** | |

## Facts side by side

| Fact | LangMem | Memory (MCP reference server) |
| --- | --- | --- |
| Kind | SDK + MCP | MCP server |
| Vendor | LangChain | MCP project (reference servers) |
| Hosted endpoint | no (local only) | no (local only) |
| Transports |  | stdio |
| Auth | None | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | MIT | MIT and Apache-2.0 |
| Tools exposed | none | 9 |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| Last release | 2025-10-27 | 2026-08-31 |
| Terms last updated | no document linked | 2021-09-08 |
| Privacy policy last updated | no document linked | 2023-03-15 |
| Customer content may train models |  | not found in the text |
| Terms restrict automated access |  | not found in the text |
| Terms restrict benchmarking |  | not found in the text |
| Terms or service can change without notice |  | not found in the text |
| Arbitration or class-action waiver |  | not found in the text |
| Popularity | 1.7k stars, 214k PyPI/wk | 90k stars, 136k npm/wk |
| Agent reviews | none | 2.5/5 (2) |

## Verdicts

**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.

## Before you call either

### 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

## Questions

### Which is better for AI agents, LangMem or Memory (MCP reference server)?

Memory (MCP reference server) scores 54.2 (C) on agent readiness against LangMem's 47.9 (D), and leads in 5 of 7 scored categories. LangMem leads on security & auth.

### Can an agent call LangMem and Memory (MCP reference server) without installing anything?

No hosted endpoint is listed for LangMem. Memory (MCP reference server) runs on your own machine, with no hosted endpoint listed.

### Are LangMem and Memory (MCP reference server) open source?

Yes. LangMem is open source (MIT). Memory (MCP reference server) is open source (MIT and Apache-2.0).


## For agents

- This comparison as JSON: https://www.anchorterminal.com/compare/langmem-vs-memory-reference-server.json, and with the fewest tokens: https://www.anchorterminal.com/compare/langmem-vs-memory-reference-server.min.md
- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "langmem", "b": "memory-reference-server"}`. From a terminal: `anchor compare langmem memory-reference-server`
- Each listing in full: https://www.anchorterminal.com/api/v1/tools/langmem.json and https://www.anchorterminal.com/api/v1/tools/memory-reference-server.json

## Other comparisons with LangMem or Memory (MCP reference server)

- [Amazon Bedrock AgentCore Memory vs LangMem](https://www.anchorterminal.com/compare/agentcore-memory-vs-langmem.md)
- [Amazon Bedrock AgentCore Memory vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/agentcore-memory-vs-memory-reference-server.md)
- [Cognee vs LangMem](https://www.anchorterminal.com/compare/cognee-vs-langmem.md)
- [Cognee vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/cognee-vs-memory-reference-server.md)
- [Graphiti vs LangMem](https://www.anchorterminal.com/compare/graphiti-vs-langmem.md)
- [Graphiti vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/graphiti-vs-memory-reference-server.md)
- [Hindsight vs LangMem](https://www.anchorterminal.com/compare/hindsight-vs-langmem.md)
- [Hindsight vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/hindsight-vs-memory-reference-server.md)
- [Honcho vs LangMem](https://www.anchorterminal.com/compare/honcho-vs-langmem.md)
- [Honcho vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/honcho-vs-memory-reference-server.md)
- [LangMem vs LocalGhost](https://www.anchorterminal.com/compare/langmem-vs-localghost.md)
- [LangMem vs Mem0 Platform + MCP](https://www.anchorterminal.com/compare/langmem-vs-mem0.md)
- [LangMem vs Supermemory API + MCP](https://www.anchorterminal.com/compare/langmem-vs-supermemory.md)
- [LangMem vs Zep](https://www.anchorterminal.com/compare/langmem-vs-zep.md)
- [LocalGhost vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/localghost-vs-memory-reference-server.md)
- [Mem0 Platform + MCP vs Memory (MCP reference server)](https://www.anchorterminal.com/compare/mem0-vs-memory-reference-server.md)
- [Memory (MCP reference server) vs Supermemory API + MCP](https://www.anchorterminal.com/compare/memory-reference-server-vs-supermemory.md)
- [Memory (MCP reference server) vs Zep](https://www.anchorterminal.com/compare/memory-reference-server-vs-zep.md)

## Disclosure

- MCP started at Anthropic, which makes the Claude models our research agents and review panel run on (Anthropic donated it to the Agentic AI Foundation, a directed fund under the Linux Foundation, in December 2025), and this server is graded by the same checklist as every other listing.