<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Opencode on M1CH's Log</title><link>https://blog.m1ch.eu/tags/opencode/</link><description>Recent content in Opencode on M1CH's Log</description><generator>Hugo</generator><language>en-us</language><copyright>Michael Klamminger</copyright><lastBuildDate>Mon, 28 Sep 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://blog.m1ch.eu/tags/opencode/index.xml" rel="self" type="application/rss+xml"/><item><title>AI Agents in My Hosting Workflow</title><link>https://blog.m1ch.eu/posts/20260928-ai-agents-in-my-hosting-workflow/</link><pubDate>Mon, 28 Sep 2026 00:00:00 +0000</pubDate><guid>https://blog.m1ch.eu/posts/20260928-ai-agents-in-my-hosting-workflow/</guid><description>&lt;p&gt;My homelab is mostly text: Docker Swarm compose files, bootc Containerfiles,
Forgejo workflows, a few Ansible playbooks and this Hugo blog. All of it lives
in git, and for years the workflow has been the same: edit in an editor, render,
deploy, check the logs, repeat.&lt;/p&gt;
&lt;p&gt;Over the last months two coding agents moved into that loop:
&lt;a href="https://opencode.ai"&gt;opencode&lt;/a&gt; and
&lt;a href="https://claude.com/claude-code"&gt;Claude Code&lt;/a&gt;. This post covers how I set them
up, what they do for me, and where I still keep my hands on the wheel.&lt;/p&gt;</description></item></channel></rss>