<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Knowledge-Stores on Unbound Force</title><link>https://unboundforce.dev/tags/knowledge-stores/</link><description>Recent content in Knowledge-Stores on Unbound Force</description><generator>Hugo</generator><language>en-US</language><copyright>Copyright (c) 2025-2026 Unbound Force</copyright><lastBuildDate>Sun, 23 Aug 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://unboundforce.dev/tags/knowledge-stores/index.xml" rel="self" type="application/rss+xml"/><item><title>Your AI Agent's Memory Survives Database Deletion — Dewey v3.1.0 Knowledge Stores</title><link>https://unboundforce.dev/blog/dewey-knowledge-stores/</link><pubDate>Sun, 23 Aug 2026 00:00:00 +0000</pubDate><guid>https://unboundforce.dev/blog/dewey-knowledge-stores/</guid><description>&lt;h2 id="the-fragility-problem"&gt;The Fragility Problem&lt;/h2&gt;
&lt;p&gt;AI agents accumulate knowledge across sessions. Decisions made during code review, patterns discovered while debugging, gotchas encountered during deployment — all of it feeds back into future work. In most agent frameworks, that knowledge lives in a single SQLite database. Delete it, corrupt it, or move to a new machine, and every learning is gone.&lt;/p&gt;</description></item></channel></rss>