<?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 mu0</title><link>https://mu0.ai/tags/agents/</link><description>Recent content in Agents on mu0</description><generator>Hugo -- 0.152.2</generator><language>en-us</language><lastBuildDate>Thu, 10 Sep 2026 08:00:00 +1000</lastBuildDate><atom:link href="https://mu0.ai/tags/agents/index.xml" rel="self" type="application/rss+xml"/><item><title>The History of the AI Agent Harness</title><link>https://mu0.ai/posts/history-of-the-agent-harness/</link><pubDate>Thu, 10 Sep 2026 08:00:00 +1000</pubDate><guid>https://mu0.ai/posts/history-of-the-agent-harness/</guid><description>Most of the recent gains in AI agents came from the software wrapped around the model, not the weights. A history of the harness in three stages — the token loop, the static harness, and the harness that improves itself — alongside YC&amp;rsquo;s own path from a shared bot to a centralised multi-user agent system.</description></item></channel></rss>