<?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>Git-Infrastructure on 兜忆轩 | Cedric's Compiler Notes</title><link>https://douyixuan.github.io/tags/git-infrastructure/</link><description>Recent content in Git-Infrastructure on 兜忆轩 | Cedric's Compiler Notes</description><image><title>兜忆轩 | Cedric's Compiler Notes</title><url>https://douyixuan.github.io/images/papermod-cover.png</url><link>https://douyixuan.github.io/images/papermod-cover.png</link></image><generator>Hugo -- 0.146.0</generator><language>en-us</language><lastBuildDate>Sat, 24 Oct 2026 08:00:00 +0800</lastBuildDate><atom:link href="https://douyixuan.github.io/tags/git-infrastructure/index.xml" rel="self" type="application/rss+xml"/><item><title>AI Native Digest 2026-10-24</title><link>https://douyixuan.github.io/posts/ai-native/2026-10-24/</link><pubDate>Sat, 24 Oct 2026 08:00:00 +0800</pubDate><guid>https://douyixuan.github.io/posts/ai-native/2026-10-24/</guid><description>今天关注 AI-native 系统规模化后的两道瓶颈：Letta 用 FrontierMemory 衡量 Agent 是否真正从过去任务中学到可迁移的经验；GitHub 则用按 Git 引用粒度并行写入和对象存储分离应对 Agent 驱动的代码流量。</description></item></channel></rss>