<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>CodeGraph on Text Matrix</title><link>https://txtmix.com/tags/codegraph/</link><description>Recent content in CodeGraph on Text Matrix</description><generator>Hugo</generator><language>zh-cn</language><lastBuildDate>Tue, 21 Jul 2026 20:06:14 +0800</lastBuildDate><atom:link href="https://txtmix.com/tags/codegraph/index.xml" rel="self" type="application/rss+xml"/><item><title>CodeGraph 深度解析：把 AI Coding Agent 的代码探索从文件扫描变成图查询</title><link>https://txtmix.com/posts/tech/codegraph-semantic-code-knowledge-graph-for-ai-coding-agents/</link><pubDate>Mon, 25 May 2026 20:16:19 +0800</pubDate><guid>https://txtmix.com/posts/tech/codegraph-semantic-code-knowledge-graph-for-ai-coding-agents/</guid><description>&lt;p>CodeGraph 把 AI Coding Agent 在大型仓库里最耗钱、也最容易失焦的一段工作提前做完了：先把代码库索引成一张可查询的图，再让 agent 沿着符号、调用关系、导入链和路由绑定去找答案。模型本身没有变强，变的是它不必每次都从 &lt;code>grep&lt;/code>、&lt;code>glob&lt;/code>、&lt;code>Read&lt;/code> 重新找路。&lt;/p></description></item></channel></rss>