<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Self-Hosted on Hullabalooing</title>
    <link>https://cruver.ai/tags/self-hosted/</link>
    <description>Recent content in Self-Hosted on Hullabalooing</description>
    <generator>Hugo</generator>
    <language>en</language>
    <lastBuildDate>Tue, 20 Jan 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://cruver.ai/tags/self-hosted/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Running Claude Code with Local LLMs via vLLM and LiteLLM</title>
      <link>https://cruver.ai/gpu-ai/posts/claude-code-local-llms-1768966311/</link>
      <pubDate>Tue, 20 Jan 2026 00:00:00 +0000</pubDate>
      <guid>https://cruver.ai/gpu-ai/posts/claude-code-local-llms-1768966311/</guid>
      <description>&lt;p&gt;Every query to Claude Code means sending my source code to Anthropic&amp;rsquo;s servers. For proprietary codebases, that&amp;rsquo;s a non-starter. With vLLM and LiteLLM, I can point Claude Code at my own hardware - keeping my code on my network while maintaining the same workflow.&lt;/p&gt;&#xA;&lt;h2 id=&#34;the-architecture&#34;&gt;The Architecture&lt;a class=&#34;anchor&#34; href=&#34;#the-architecture&#34;&gt;#&lt;/a&gt;&lt;/h2&gt;&#xA;&lt;p&gt;The trick is that Claude Code expects the Anthropic Messages API, but local inference servers speak OpenAI&amp;rsquo;s API format. LiteLLM bridges this gap. It accepts Anthropic-formatted requests and translates them to OpenAI format for my local vLLM instance.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
