memodb-io/memobase

Structures user data into dynamically-evolving profiles and timestamped event timelines, enabling sub-100ms memory retrieval through SQL queries rather than vector search. Supports Python, Node.js, and Go SDKs with batch processing buffers to reduce LLM token costs by 40-50%, and includes a Model Context Protocol (MCP) server for seamless integration with AI frameworks. Achieves state-of-the-art performance on the LOCOMO benchmark while maintaining configurable memory schemas, allowing developers to define precisely which user attributes their applications capture.

2,599 stars and 3,687 monthly downloads. Available on PyPI.