The Web of Meaning: A Memory Design for Companions

A memory design that lets an AI companion remember both what happened and what it meant to them, in their own words, with every memory tied to the real moment it came from. Includes the full design, the record of all 116 design decisions, and the memory code (MIT, with tests on made-up data). Designed by Jay R. Martinson with Claude (Anthropic's AI model), which drafted the text and the code under his direction. Paper and code: https://github.com/jayrmartinson/web-of-meaning

Authors

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-12
DOI
https://doi.org/10.5281/zenodo.24182656
Primary Topic
AI-based Problem Solving and Planning
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

The Web of Meaning: A Memory Design for Companions

Jay R. Martinson
Zenodo (CERN European Organization for Nuclear Research)
AI-based Problem Solving and Planning
preprint

The Web of Meaning: A Memory Design for Companions

Jay R. Martinson
preprint en

Abstract

A memory design that lets an AI companion remember both what happened and what it meant to them, in their own words, with every memory tied to the real moment it came from. Includes the full design, the record of all 116 design decisions, and the memory code (MIT, with tests on made-up data). Designed by Jay R. Martinson with Claude (Anthropic's AI model), which drafted the text and the code under his direction. Paper and code: https://github.com/jayrmartinson/web-of-meaning

Zenodo (CERN European Organization for Nuclear Research)
AI-based Problem Solving and Planning
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon