Memory & evals · Project

LangMem

LangMem provides Python components for extracting, storing and retrieving long-term agent memory.

+ Follow

Builder facts

  • In-turn tools. An agent can call memory management and search tools during a conversation. Both use LangGraph store namespaces. Source ↗
  • Background extraction. A background memory manager can extract, consolidate and update memories outside the interactive turn. Functional primitives also support custom storage. Source ↗
  • Persistence. LangGraph’s in-memory store loses data on restart. A database-backed store such as AsyncPostgresStore provides persistence. Source ↗
  • Access. The MIT-licensed Python package integrates with a configured language model. Storage and any hosted model usage are supplied separately. Source ↗

Sources checked

Publisher update ·

LangMem 0.0.30 ↗

The Python package widened its LangGraph dependency from >=0.6,<0.7 to >=0.6,<2.

Change timeline

0 stories

No verified releases in this timeline yet.