<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:sy="http://purl.org/rss/1.0/modules/syndication/" xmlns:media="http://search.yahoo.com/mrss/"><channel><title>Headroom on Shaowen Chen's Website</title><link>https://www.chenshaowen.com/en/tags/headroom/</link><description>Recent content in Headroom on Shaowen Chen's Website</description><generator>Hugo -- gohugo.io</generator><language>en</language><copyright>&amp;copy;2016 - {year}, All Rights Reserved.</copyright><lastBuildDate>Fri, 03 Jul 2026 00:00:00 +0000</lastBuildDate><sy:updatePeriod>weekly</sy:updatePeriod><atom:link href="https://www.chenshaowen.com/en/tags/headroom/atom.xml" rel="self" type="application/rss+xml"/><item><title>Headroom: Making AI Coding Assistants Save More Tokens</title><link>https://www.chenshaowen.com/en/blog/headroom-reduce-ai-agent-tokens.html</link><pubDate>Fri, 03 Jul 2026 00:00:00 +0000</pubDate><atom:modified>Fri, 03 Jul 2026 00:00:00 +0000</atom:modified><guid>https://www.chenshaowen.com/en/blog/headroom-reduce-ai-agent-tokens.html</guid><description>1. What Headroom Is Headroom is a context compression layer for AI agents. Before the LLM receives a request, it performs content-aware compression on tool output, logs, RAG chunks, file contents, and conversation history, cutting token usage to 5%–40% of the original while keeping answer quality as unchanged as possible.</description><dc:creator>微信公众号</dc:creator><category>AI</category><category>MCP</category><category>Cursor</category><category>Headroom</category><category>R&amp;D</category></item></channel></rss>