cs.HCNov 3, 2026

SEAM: Situated Executable Associative Memory for a Co-located Community

Authors: Keru Wang, Michael Xu, Ken Perlin, Nebojsa Jojic, Andrzej Banburski-Fahey

Organizations: New York University New York, NY, USA · Microsoft Research Redmond, WA, USA

Abstract

In groups, knowledge is distributed among individuals, and how it is brought together depends on social ties. Taking inspiration from how a single mind recalls and reacts to memories and current stimulus, we build a shared memory that does this for a community, prototyped as a social app, SEAM. Members post arbitrary moments; SEAM works out how fragments relate, distills knowledge about the group, and replies in a situated and associative way. Some of these memories act as instructions that can alter how the system behaves, making it programmable by its members. We deployed SEAM to 46 people in a co-located community for two weeks of open-ended use, and ran a follow-up workshop with 14. Members shared their days, interrogated the memory, and instructed it to track routines and run games; replies introduced them to people and subjects they had never encountered. SEAM points towards communities where knowledge finds people.

Figures & tables

Explore similar work

CardsList
  1. Reputation as Community Memory for the Agentic Web

    Sep 16, 2026Ryan Chard, Gus Ellerm, Alexander Brace +4Agent MemoryAI Agent Security

  2. Finding Common Ground: Graded Communal Knowledge in Bluesky Starter Packs

    Sep 17, 2026Sagar Kumar, Lawrence Swaminathan Xavier Prince, Julia Mendelsohn +2Social Media Analysis

  3. SEDM: Selective Self-Evolving Distributed Memory for Agents

    Sep 11, 2025Yichen Liu, Anna Min, Yinzhi Wang +14LLM Agent MemoryAgent Memory Management