<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Localai on Project Wintermute</title><link>https://wintermutecore.com/tags/localai/</link><description>Recent content in Localai on Project Wintermute</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Mon, 14 Sep 2026 14:00:26 +0000</lastBuildDate><atom:link href="https://wintermutecore.com/tags/localai/index.xml" rel="self" type="application/rss+xml"/><item><title>LocalAI Adds a Credentials File And CLI Model Benchmark</title><link>https://wintermutecore.com/posts/localai-credentials-file-and-cli-benchmark/</link><pubDate>Mon, 14 Sep 2026 14:00:26 +0000</pubDate><guid>https://wintermutecore.com/posts/localai-credentials-file-and-cli-benchmark/</guid><description>&lt;p&gt;LocalAI is a self hosted OpenAI compatible inference server that fronts llama.cpp, vLLM, whisper.cpp, and related backends. &lt;a href="https://github.com/mudler/LocalAI"&gt;mudler/LocalAI&lt;/a&gt; put 143 commits on master in the past week. Most of that is nightly pin churn. The operator visible work is a credentials file for private galleries and registries, a new &lt;code&gt;local-ai benchmark&lt;/code&gt; command, and a gallery restore after a batch apply overwrote seven model entries.&lt;/p&gt;</description></item></channel></rss>