<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Context Offload on Text Matrix</title><link>https://txtmix.com/tags/context-offload/</link><description>Recent content in Context Offload on Text Matrix</description><generator>Hugo</generator><language>zh-cn</language><lastBuildDate>Sat, 23 May 2026 08:55:34 +0800</lastBuildDate><atom:link href="https://txtmix.com/tags/context-offload/index.xml" rel="self" type="application/rss+xml"/><item><title>TencentDB Agent Memory：把 Agent 记忆从聊天历史改造成分层信息系统</title><link>https://txtmix.com/posts/tech/tencentdb-agent-memory/</link><pubDate>Fri, 15 May 2026 18:22:00 +0800</pubDate><guid>https://txtmix.com/posts/tech/tencentdb-agent-memory/</guid><description>&lt;p>大多数 Agent memory 项目都把问题定义得过窄：要么给历史做 embedding，要么定期做摘要。TencentDB Agent Memory 的可取之处，在于它先承认“记忆”其实包含两类完全不同的工程问题：跨会话经验沉淀，以及单次长任务里的上下文治理。&lt;/p></description></item></channel></rss>