<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Agents on zolty.systems</title><link>https://blog.zolty.systems/tags/agents/</link><description>Recent content in Agents on zolty.systems</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Tue, 21 Apr 2026 01:00:00 -0400</lastBuildDate><atom:link href="https://blog.zolty.systems/tags/agents/index.xml" rel="self" type="application/rss+xml"/><item><title>Giving Claude the ability to talk back: agentic long-running processes in OpenClaw</title><link>https://blog.zolty.systems/posts/2026-04-21-claude-agentic-openclaw-long-running-talkback/</link><pubDate>Tue, 21 Apr 2026 01:00:00 -0400</pubDate><guid>https://blog.zolty.systems/posts/2026-04-21-claude-agentic-openclaw-long-running-talkback/</guid><description>How I wire Claude into OpenClaw — my homelab&amp;#39;s autonomous ops + trading intelligence platform — so long-running agents can think, act, and interrupt me in Slack when something needs a human. The goal was never chat. It&amp;#39;s an agent that finishes a six-hour job and waves a hand.</description></item></channel></rss>