# widemem.ai

An open source AI memory layer that scores how important a fact is and decays it over time at different rates, so a critical detail such as a medical allergy outranks a passing preference.

widemem organizes memory in three layers: individual facts roll up into summaries, and summaries roll up into broader themes, so a narrow question returns a specific fact while a broad question returns the bigger picture. Facts are scored for importance on a 1 to 10 scale and combined with time decay, so a critical, potentially life-affecting fact is retained and surfaced ahead of routine daily details even as time passes, and the project describes a "your money or your life" classification step that flags this kind of high-stakes content specifically.

It is positioned as a local-first, batteries-included alternative to relying on a growing context window or a generic RAG pipeline that treats every stored fact the same way and lets contradictions accumulate silently. It is written in Python and integrates with embeddings, vector search and MCP for use from AI coding and assistant tools.

Website: https://widemem.ai