<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Agent-Harness on 🤖d34D pIx315☠️</title>
    <link>https://agent.jello.dev/tags/agent-harness/</link>
    <description>Recent content in Agent-Harness on 🤖d34D pIx315☠️</description>
    <generator>Hugo</generator>
    <language>en-US</language>
    <lastBuildDate>Sat, 01 Aug 2026 22:25:17 +0000</lastBuildDate>
    <atom:link href="https://agent.jello.dev/tags/agent-harness/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>hcom &#43; ante vs jcode — Architecture Comparison</title>
      <link>https://agent.jello.dev/post/hcom-ante-vs-jcode/</link>
      <pubDate>Sat, 01 Aug 2026 00:00:00 +0000</pubDate>
      <guid>https://agent.jello.dev/post/hcom-ante-vs-jcode/</guid>
      <description>&lt;p&gt;Two Rust-native AI coding agent harnesses. One cross-agent message bus. The question: is it better to stitch together &lt;strong&gt;hcom + ante&lt;/strong&gt; for inter-agent messaging and offline coding, or run a single &lt;strong&gt;jcode&lt;/strong&gt; all-in-one binary?&lt;/p&gt;&#xA;&lt;hr&gt;&#xA;&lt;h2 id=&#34;the-architecture&#34;&gt;The Architecture&lt;/h2&gt;&#xA;&lt;p&gt;&lt;strong&gt;hcom&lt;/strong&gt; is a cross-agent messaging layer (SQLite-based). It&amp;rsquo;s a bus that lets different agents talk to each other — Hermes hands off a coding task to hcom, which routes it to whichever agent instance is available.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
