<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Memory on nmnhut</title><link>https://nmnhut.dev/tags/memory/</link><description>Recent content in Memory on nmnhut</description><generator>Hugo -- 0.157.0</generator><language>en-us</language><lastBuildDate>Fri, 10 Apr 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://nmnhut.dev/tags/memory/index.xml" rel="self" type="application/rss+xml"/><item><title>MAGMA: Teaching AI to Remember Like Humans Do</title><link>https://nmnhut.dev/posts/magma-multi-graph-memory-for-ai/</link><pubDate>Fri, 10 Apr 2026 00:00:00 +0000</pubDate><guid>https://nmnhut.dev/posts/magma-multi-graph-memory-for-ai/</guid><description>The MAGMA paper proposes a multi-graph memory architecture that separates semantic, temporal, causal, and entity relationships — giving AI agents structured recall instead of keyword matching.</description></item></channel></rss>