<?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>Context Engineering on MK's Lab</title><link>https://blog.mklee.org/tags/context-engineering/</link><description>Recent content in Context Engineering on MK's Lab</description><generator>Hugo -- 0.146.0</generator><language>zh-tw</language><lastBuildDate>Sat, 28 Mar 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://blog.mklee.org/tags/context-engineering/index.xml" rel="self" type="application/rss+xml"/><item><title>AI Agent 記憶的 Context Tree：從日誌地獄到兩層架構</title><link>https://blog.mklee.org/posts/context-tree-agent-memory/</link><pubDate>Sat, 28 Mar 2026 00:00:00 +0000</pubDate><guid>https://blog.mklee.org/posts/context-tree-agent-memory/</guid><description>當 AI agent 的記憶系統塞滿了 37 個檔案，65% 是噪音，你需要的不是更大的 context window，而是更好的架構。這是把扁平日誌改造成 journal + knowledge 兩層記憶的實戰記錄。</description></item></channel></rss>