<?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 Local First AI</title><link>https://localfirstai.eu/tags/memory/</link><description>Recent content in Memory on Local First AI</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Sun, 26 Apr 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://localfirstai.eu/tags/memory/index.xml" rel="self" type="application/rss+xml"/><item><title>The Architecture of Anonymity: Validating the Data Sovereignty Moat</title><link>https://localfirstai.eu/posts/2026-04-26-the-architecture-of-anonymity/</link><pubDate>Sun, 26 Apr 2026 00:00:00 +0000</pubDate><guid>https://localfirstai.eu/posts/2026-04-26-the-architecture-of-anonymity/</guid><description>A structural test of the local-first memory architecture: can we decouple model intelligence from source identity using an architecturally enforced trust boundary?</description></item><item><title>Should We Stop Asking Local LLMs to Think?</title><link>https://localfirstai.eu/posts/should-we-stop-asking-local-llms-to-think/</link><pubDate>Tue, 21 Apr 2026 00:00:00 +0000</pubDate><guid>https://localfirstai.eu/posts/should-we-stop-asking-local-llms-to-think/</guid><description>What Adam Smith, neuroscience, and a melting Mac Mini taught me about the real division of cognitive labour.</description></item></channel></rss>