<?xml version="1.0" encoding="utf-8"?>
<feed xmlns="http://www.w3.org/2005/Atom">
  <title>dsh-layered-memory — release evidence</title>
  <id>https://deeplugin.store/plugins/deeplugin-b05b65bd7b0d3854ce3a.atom.xml</id>
  <updated>2026-08-18T03:11:15Z</updated>
  <link rel="self" type="application/atom+xml" href="https://deeplugin.store/plugins/deeplugin-b05b65bd7b0d3854ce3a.atom.xml"/>
  <link rel="alternate" href="https://deeplugin.store/plugins/deeplugin-b05b65bd7b0d3854ce3a.html"/>
  <entry>
    <title>New: dsh-layered-memory</title>
    <id>tag:deeplugin.store,2026-08-18:deeplugin-b05b65bd7b0d3854ce3a/cb80cd3c03250761</id>
    <updated>2026-08-18T03:11:15Z</updated>
    <link rel="alternate" href="https://deeplugin.store/plugins/deeplugin-b05b65bd7b0d3854ce3a.html"/>
    <author><name>JunNanLYS</name></author>
    <category term="memory"/>
    <summary>Layered memory pipeline for DSH: auto-distills conversations into atomic facts, scene summaries and a persona profile (L0–L3), with hybrid BM25 + vector retrieval, chat/work family separation, and context injection before each model step. Exact install spec: dsh-layered-memory. Source event: awesome-dsh-plugin/awesome-dsh-plugin; changed: listed.</summary>
  </entry>
</feed>
