Back to directory

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.ai

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.

More in Agent memory

See all 450
  • A long technical guide to AI agent memory: why stateless LLMs need it, the different memory architectures from vector stores to knowledge graphs, and how Cognee implements one as an open-source memory layer.

  • A local, file-based long-term memory layer for a personal AI that never summarizes conversations, keeping every line with a timestamp and searching by time first and words second, rather than retrieving only similar-seeming chunks.

  • NEOTH

    deepwiki.com

    A local-first personal AI daemon in Rust with five memory tiers, consent-gated tools, a WASM plugin sandbox, multi-provider model routing and signed audit logs, aimed at people who want both a daily assistant and a serious coding helper.