Building Shared Memory for AI Agents in Notion

Summary

Lore is an open-source, MIT-licensed tool from Notion for giving AI agents shared, persistent memory backed by Notion, addressing experiential knowledge, follow-up tasks, decision records, and procedures that can disappear between sessions. A Lore vault uses five related Notion databases—Projects, Topics, Memories, Entities, and Facts—with MCP tools for agents, Notion or a CLI for humans, and hooks intended to retrieve context and save information in the background. The design emphasizes memory maintenance: facts expire by default, relationships such as supersedes and conflicts_with clarify updates, and the CLI can identify orphaned or duplicated information. In a 500-query SkillRet retrieval evaluation, Lore achieved 84% success, while a paired model evaluation found seeded memory recovered about 46% of failures on tasks never solved without memory. The results indicate that relevant, well-maintained memory can improve agent performance, while stale or irrelevant content can harm it.

Takeaways

1. 1

   Lore vaults organize memory across Projects, Topics, Memories, Entities, and Facts, with relations that support predictable searching and information discovery.

2. 2

   Facts expire by default, and relationships such as supersedes, scoped, and conflicts_with make updates explicit; the CLI can find orphaned facts, duplicates, and other memory debt.

3. 3

   In evaluations, Lore achieved 84% success on 500 SkillRet queries, and seeded memory recovered about 46% of failures on tasks the no-memory agent never solved.