<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Hermes-Agent on Danilo Falcão da Silva</title><link>https://falcao.org/tags/hermes-agent/</link><description>Recent content in Hermes-Agent on Danilo Falcão da Silva</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Wed, 20 May 2026 14:30:00 -0300</lastBuildDate><atom:link href="https://falcao.org/tags/hermes-agent/index.xml" rel="self" type="application/rss+xml"/><item><title>Hermes Agent vs OpenClaw: Why I Run Hermes Every Day</title><link>https://falcao.org/posts/hermes-agent-vs-openclaw/</link><pubDate>Wed, 20 May 2026 14:30:00 -0300</pubDate><guid>https://falcao.org/posts/hermes-agent-vs-openclaw/</guid><description>&lt;p>There are two open-source autonomous agents in 2026 worth a serious
DevOps engineer&amp;rsquo;s time, and they have made &lt;strong>opposite architectural
bets&lt;/strong>. I tried both. I run Hermes Agent every day. This is the
analysis of why — not a both-sides post, not a head-to-head benchmark,
but a direct argument that one of these two architectures is right for
infrastructure work and the other one isn&amp;rsquo;t.&lt;/p>
&lt;p>The headline: &lt;strong>agent-first beats gateway-first when the work rewards
familiarity.&lt;/strong> Most infrastructure work does. The rest of this post is
the why.&lt;/p></description></item></channel></rss>