<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/">
  <channel>
    <title>Agents on Bryan Chasko&#39;s Portfolio</title>
    <link>https://bryanchasko.com/tags/agents/</link>
    <description>Recent content in Agents on Bryan Chasko&#39;s Portfolio</description>
    <image>
      <title>Bryan Chasko&#39;s Portfolio</title>
      <url>https://bryanchasko.com/%3Clink%20or%20path%20of%20image%20for%20opengraph,%20twitter-cards%3E</url>
      <link>https://bryanchasko.com/%3Clink%20or%20path%20of%20image%20for%20opengraph,%20twitter-cards%3E</link>
    </image>
    <generator>Hugo -- 0.152.2</generator>
    <language>en</language>
    <lastBuildDate>Mon, 31 Aug 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://bryanchasko.com/tags/agents/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Muse Glimmer on HeraldStack: Local 30B Agents, One GPU, No Cloud</title>
      <link>https://bryanchasko.com/posts/muse-glimmer-heraldstack-agents-2026-08-31/</link>
      <pubDate>Mon, 31 Aug 2026 00:00:00 +0000</pubDate>
      <guid>https://bryanchasko.com/posts/muse-glimmer-heraldstack-agents-2026-08-31/</guid>
      <description>How we hooked Meta&amp;rsquo;s Muse Glimmer 30B into a local agent fleet on a single RX 6700 XT — on-demand llama.cpp, Valkey gpu_lock, Ollama, ComfyUI, and a Firecracker microVM that delegates from Spark to Glimmer.</description>
    </item>
  </channel>
</rss>
