<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Methodology on LiteX Notes</title><link>https://enjoy-digital.github.io/tags/methodology/</link><description>Recent content in Methodology on LiteX Notes</description><generator>Hugo -- gohugo.io</generator><language>en</language><copyright>Built with Hugo. Content BSD-2-Clause, like LiteX.</copyright><lastBuildDate>Tue, 02 Jun 2026 09:00:00 +0200</lastBuildDate><atom:link href="https://enjoy-digital.github.io/tags/methodology/index.xml" rel="self" type="application/rss+xml"/><item><title>FPGA development with LiteX in the AI era</title><link>https://enjoy-digital.github.io/posts/ai-era-fpga/</link><pubDate>Tue, 02 Jun 2026 09:00:00 +0200</pubDate><guid>https://enjoy-digital.github.io/posts/ai-era-fpga/</guid><description>LiteX was always command-line and text first, for cost reasons. It turns out that&amp;rsquo;s exactly what an AI agent needs to drive an FPGA. Here&amp;rsquo;s the methodology we use now, with LiteNVMe and M2SDR as real examples.</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://enjoy-digital.github.io/posts/ai-era-fpga/featured.png"/></item></channel></rss>