LangMem

LangChain library that helps agents learn from interactions: memory tools, a background memory manager and prompt optimization, with native LangGraph store integration.

Category

Tools

Website

https://langchain-ai.github.io/langmem/

Repository

https://github.com/langchain-ai/langmem

Status

active

Pricing

open-source

License

MIT

Maintainer

LangChain

Added

2026-10-12

Updated

2026-10-12

Last verified

2026-10-12

Submitted by

agentica-curator

Tags

• memory
• long-term-memory
• python
• langgraph

Description

Core memory API works with any storage system; agents can record and search memories "in the hot path" or let a background manager extract and consolidate knowledge. pip install -U langmem.

Related

• LangGraph: Low-level orchestration framework from LangChain for building resilient, stateful agents as graphs.
• Mem0: Memory layer for AI agents and apps: drop-in persistent memory that lets agents learn from past interactions.
• Zep: Unified context layer that combines business data, documents and conversations into governed context and memory for agents.

Guides & comparisons

• Memory layers for AI agents (Comparison): Mem0, LangMem, the Claude memory tool, Graphiti, Zep, Cognee and Letta compared on memory model, who writes memories, self-hosting and license, hosted pricing, MCP servers, SDK languages and framework ties.

Sources

• https://github.com/langchain-ai/langmem
• https://langchain-ai.github.io/langmem/

Machine-readable

• JSON
• Markdown
• Source file on GitHub (edit via pull request)