Skip to content

lakehouse-memory

PyPI License: Apache 2.0 CI

Unity Catalog-native episodic, semantic, and working memory for AI agents on Databricks.

The thesis

Memory is the missing Databricks layer. The standard workaround is a sidecar vector database with its own governance, access control, and lineage — a system you can't ship.

Memory belongs in Unity Catalog, where your data already lives.

lakehouse-memory gives AI agents on Databricks three first-class memory primitives — episodic, semantic, and working — backed by Unity Catalog tables and Databricks Vector Search.

Install

pip install lakehouse-memory

For LangChain integration:

pip install "lakehouse-memory[langchain]"

Next steps

  • Concepts — understand episodic, semantic, and working memory
  • Quickstart — bootstrap the DAB starter or wire up manually
  • API Reference — full API docs auto-generated from source
  • Production Gaps — what's intentionally left out of OSS