<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Rag on Jeff Mixon | jeffmixon.com</title><link>https://www.jeffmixon.com/tags/rag/</link><description>Recent content in Rag on Jeff Mixon | jeffmixon.com</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Mon, 13 Jul 2026 22:55:33 -0700</lastBuildDate><atom:link href="https://www.jeffmixon.com/tags/rag/index.xml" rel="self" type="application/rss+xml"/><item><title>Corpusly: a Google Drive index with no server, no cloud embeddings, and no mirrored files</title><link>https://www.jeffmixon.com/post/corpusly-local-first-rag-mcp/</link><pubDate>Mon, 13 Jul 2026 00:00:00 -0700</pubDate><guid>https://www.jeffmixon.com/post/corpusly-local-first-rag-mcp/</guid><description>Corpusly indexes a Google Drive for semantic search and serves it to Claude and other MCP clients, with no vendor server anywhere in the data path. A look at the local embedding pipeline built on a quantized, in-process transformers.js model, the two-transport MCP server it&amp;rsquo;s served over, and the engineering it took to make &amp;rsquo;nothing leaves the machine&amp;rsquo; actually true: a memory blowout fixed by sub-batching, a stdout-corruption constraint solved structurally, and an OAuth scope decision that doubled as a compliance strategy.</description></item></channel></rss>