<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Cline on Landry Zetam - Tech Blog</title><link>https://blog.landryzetam.net/tags/cline/</link><description>Recent content in Cline on Landry Zetam - Tech Blog</description><generator>Hugo -- gohugo.io</generator><language>en-us</language><lastBuildDate>Fri, 08 Aug 2025 00:00:00 +0000</lastBuildDate><atom:link href="https://blog.landryzetam.net/tags/cline/index.xml" rel="self" type="application/rss+xml"/><item><title>Powering Open WebUI and Cline with GPUStack: My AI Infrastructure Journey</title><link>https://blog.landryzetam.net/posts/local-ai-open-webui-cline/</link><pubDate>Fri, 08 Aug 2025 00:00:00 +0000</pubDate><guid>https://blog.landryzetam.net/posts/local-ai-open-webui-cline/</guid><description>&lt;p>After building my Mac AI cluster, I needed a way to make it accessible to all my tools. The journey took me through several frameworks before landing on the perfect solution: GPUStack providing an OpenAI-compatible API that seamlessly integrates with everything.&lt;/p>
&lt;h2 id="the-evolution-finding-the-right-framework">The Evolution: Finding the Right Framework&lt;/h2>
&lt;h3 id="the-journey">The Journey&lt;/h3>
&lt;p>My path to the current setup wasn&amp;rsquo;t straightforward:&lt;/p>
&lt;ol>
&lt;li>&lt;strong>MLX Distributed Computing&lt;/strong>: Started here for model training and local inference on Apple Silicon&lt;/li>
&lt;li>&lt;strong>Exo Labs&lt;/strong>: Experimented with this promising framework, but pivoted when the community began a redesign&lt;/li>
&lt;li>&lt;strong>GPUStack&lt;/strong>: The solution that finally clicked - providing OpenAI-compatible endpoints that work with everything&lt;/li>
&lt;/ol>
&lt;h2 id="the-current-architecture">The Current Architecture&lt;/h2>
&lt;p>Here&amp;rsquo;s how my AI infrastructure actually works:&lt;/p></description></item></channel></rss>