<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Terminal on Igor Kulman</title>
    <link>https://blog.kulman.sk/tags/terminal/</link>
    <description>Recent content in Terminal on Igor Kulman</description>
    <generator>Hugo -- gohugo.io</generator>
    <language>en-us</language>
    <lastBuildDate>Wed, 16 Sep 2026 05:29:12 +0100</lastBuildDate><atom:link href="https://blog.kulman.sk/tags/terminal/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>My terminal-native setup for parallel coding agents</title>
      <link>https://blog.kulman.sk/terminal-native-setup-for-parallel-coding-agents/</link>
      <pubDate>Wed, 16 Sep 2026 05:29:12 +0100</pubDate>
      
      <guid>https://blog.kulman.sk/terminal-native-setup-for-parallel-coding-agents/</guid>
      <description>In my previous post about Pi, I wrote about wanting a stable coding harness while the models underneath it keep changing. But one agent in one terminal is not the whole workflow. I increasingly have several agents working at once, sometimes in the same repository.
The surprising part is that I manage that with a simpler stack: a terminal, Git worktrees, and a terminal multiplexer built for agents.
My current setup is mostly Ghostty, Git worktrees, Herdr, and hunk.</description>
    </item>
    
  </channel>
</rss>
