<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Reliability on Meditations of a CTO</title><link>https://kristophmatthews.com/tags/reliability/</link><description>Recent content in Reliability on Meditations of a CTO</description><generator>Hugo</generator><language>en-us</language><copyright>© 2025 Kristoph Matthews</copyright><lastBuildDate>Mon, 12 Oct 2026 19:03:59 -0400</lastBuildDate><atom:link href="https://kristophmatthews.com/tags/reliability/index.xml" rel="self" type="application/rss+xml"/><item><title>Setting up a UPS and NUT for stable local agents</title><link>https://kristophmatthews.com/posts/setting-up-a-ups-for-stable-local-agents/</link><pubDate>Mon, 12 Oct 2026 19:03:59 -0400</pubDate><guid>https://kristophmatthews.com/posts/setting-up-a-ups-for-stable-local-agents/</guid><description>&lt;p>Earlier this year, I built a custom souped-up rig to run all of my AI agents at home, regardless of where I am, and without consuming resources on my own machine. It&amp;rsquo;s headless, so I SSH into it as if it were a cloud-based VM.
&lt;em>10 docker containers to build and test code, all at once?&lt;/em> No problem. &lt;em>A two hour drive to the city or to a customer site that would normally be lost productivity?&lt;/em>
Not even- my rig is chomping away at tasks while my Macbook lid is clammed shut and packed away.&lt;/p></description></item></channel></rss>