# LangMem (slim)

> LangMem is LangChain's open-source Python library for long-term agent memory. It extracts facts from conversations with an LLM, stores and searches them in a LangGraph store the owner runs, and includes two memory tools, message summarisation and prompt optimisation.

- Full: https://www.anchorterminal.com/tools/langmem.md (~5,800 tokens) · this version ~1,330 tokens · JSON https://www.anchorterminal.com/tools/langmem.json · canonical https://www.anchorterminal.com/tools/langmem
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-09

**D · 47.9/100 · rank #734 of 842 · #9 in Agent memory · not agent-ready · confidence medium**


Assessment: 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.

## Facts

- Kind: SDK + MCP · vendor: LangChain · category: Agent memory · legal entity: LangChain (the licence file gives no legal form) · provenance 55/100
- Packages: pypi `langmem`
- Auth: None · pricing: Free · x402: no · licence: MIT
- Probe metrics: not measured yet (probes haven't run)
- Interface: Python library, `langmem` 0.0.30 on PyPI. No HTTP API, MCP server, CLI or npm package
- Agent tools: Two LangChain tools. `manage_memory` (create, update, delete) and `search_memory` (query, limit, offset, filter)
- Background memory: `create_memory_manager` returns extracted memories. `create_memory_store_manager` searches, inserts, updates and optionally deletes in the store. `ReflectionExecutor` delays and debounces the work
- Storage: Any LangGraph `BaseStore` the owner supplies. The docs use `InMemoryStore` and name `AsyncPostgresStore` for production
- Models: Any LangChain chat model by name or instance. `langchain-openai` and `langchain-anthropic` are required dependencies
- Other modules: Message summarisation (`langmem.short_term`) and prompt optimisers (`create_prompt_optimizer`, `create_multi_prompt_optimizer`)
- Python: Declares 3.10 or later. Source on main needs 3.11 for `typing.NotRequired`
- Cost: Free software. LLM calls for extraction, embedding calls for search and the database are the owner's

- Scores: Reliability 32, Performance pending, Schema & documentation 55, Agent ergonomics 66, Security & auth 45, Payments & pricing 60, Task success pending, Maintenance & community 15, Transparency & trust 59 · total over the 7 assessed categories
- Why: Reliability, Local-software reading. · Schema & documentation, Library reading, with the tool lines applied to the two agent tools. · Agent ergonomics, Two tools with short descriptions (25). · Security & auth, Local-software reading. · Payments & pricing, MIT-licensed package the owner runs, with nothing to buy for LangMem itself, read with the self-hosted rule. · Maintenance & community, 0.0.30 reached PyPI on 27 October 2025, 346 days before the check (0). · Transparency & trust, MIT licence in the repository and on PyPI (30).
- Sources: 15, open questions: 6, both in the full twin
- Capabilities: memory.store, memory.search, memory.user, memory.delete
- JSON: https://www.anchorterminal.com/api/v1/tools/langmem.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/langmem.svg` or a link to https://www.anchorterminal.com/tools/langmem from a page on langchain.com or one of its subdomains, or the README of github.com/langchain-ai/langmem, then `POST https://www.anchorterminal.com/api/v1/verify` `{"slug", "url"}` or `verify_listing` at /mcp; re-checked weekly, no effect on the grade. Snippets in the full twin.

## Before you call it

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

## Connect

```bash
pip install -U langmem
```
Full config and headless snippets are in the full page. Through letme (picks today, calling later): https://letme.dev/langmem

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| Amazon Bedrock AgentCore Memory | A | 79.4 | memory.store, memory.search, memory.user, memory.delete | https://www.anchorterminal.com/tools/agentcore-memory.min.md |
| Zep | B | 69.3 | memory.store, memory.search, memory.user, memory.delete | https://www.anchorterminal.com/tools/zep.min.md |
| Honcho | B | 64.1 | memory.store, memory.search, memory.user, memory.delete | https://www.anchorterminal.com/tools/honcho.min.md |
| Supermemory API + MCP | B | 63.6 | memory.store, memory.search, memory.user, memory.delete | https://www.anchorterminal.com/tools/supermemory.min.md |
| Mem0 Platform + MCP | C | 56.1 | memory.store, memory.search, memory.user, memory.delete | https://www.anchorterminal.com/tools/mem0.min.md |


## Panel reviews (0, desk reviews from public material, no calls made)