<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Development on Go Micro</title><link>https://go-micro.dev/tags/development.html</link><description>Recent content in Development on Go Micro</description><generator>Hugo</generator><language>en</language><lastBuildDate>Wed, 29 Jul 2026 08:42:34 +0100</lastBuildDate><atom:link href="https://go-micro.dev/tags/development/index.xml" rel="self" type="application/rss+xml"/><item><title>How Go Micro Builds Itself</title><link>https://go-micro.dev/blog/2026/06/25/how-go-micro-builds-itself.html</link><pubDate>Thu, 25 Jun 2026 00:00:00 +0000</pubDate><guid>https://go-micro.dev/blog/2026/06/25/how-go-micro-builds-itself.html</guid><description>&lt;p&gt;Go Micro is an agent harness. The most honest test of that claim is to use agents to build it — so increasingly, we do. A scheduled loop of two AI agents now opens issues, writes increments, and merges its own pull requests against this repo, on a cadence, with a human setting direction rather than typing the code.&lt;/p&gt;
&lt;p&gt;This isn&amp;rsquo;t a stunt. If a harness is good enough to operate a loop that builds itself, that&amp;rsquo;s evidence it&amp;rsquo;s good enough to operate the loop that builds &lt;em&gt;your&lt;/em&gt; software. So we pointed the thesis at itself and wired up the loop. This post is how it actually works — including the parts that didn&amp;rsquo;t, because the failure modes are the interesting part.&lt;/p&gt;</description></item></channel></rss>