<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Accessibility Tree on SoloSoft</title><link>https://www.solosoft.dev/tags/accessibility-tree/</link><description>Recent content in Accessibility Tree on SoloSoft</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Fri, 06 Nov 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://www.solosoft.dev/tags/accessibility-tree/index.xml" rel="self" type="application/rss+xml"/><item><title>agent-desktop Audited: 16,842 Stars, 42 Watchers, and 44 Commands That Answer PERM_DENIED Where No Permission Exists</title><link>https://www.solosoft.dev/post/agent-desktop-audit-44-perm-denied-no-permission/</link><pubDate>Fri, 06 Nov 2026 00:00:00 +0000</pubDate><guid>https://www.solosoft.dev/post/agent-desktop-audit-44-perm-denied-no-permission/</guid><description>&lt;p&gt;Vercel Labs has a habit of shipping small tools that look like demos and turn out to be infrastructure. &lt;code&gt;agent-desktop&lt;/code&gt; is the version of that habit aimed at a genuinely hard problem: letting an AI agent drive a desktop application without screenshots and without pixel matching.&lt;/p&gt;
&lt;p&gt;The pitch is one paragraph long, and it is the right paragraph. The agent reads the operating system&amp;rsquo;s accessibility tree, gets JSON back, clicks a &lt;code&gt;ref&lt;/code&gt;, reads the UI again. No model inside, no vision model in the loop, no coordinates guessed from an image. The GitHub repository has 16,842 stars, was created on 2026-02-19, and shipped version 1.2.0 on 2026-11-05.&lt;/p&gt;</description></item></channel></rss>