<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>SSH on Farid</title><link>https://polymatx.dev/blog/tags/ssh/</link><description>Recent content in SSH on Farid</description><generator>Hugo</generator><language>en</language><lastBuildDate>Tue, 06 Oct 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://polymatx.dev/blog/tags/ssh/index.xml" rel="self" type="application/rss+xml"/><item><title>Why AI Agents Shouldn't Get a Shell on Your Servers (So I Built Opsgate)</title><link>https://polymatx.dev/blog/posts/opsgate-ai-agents-without-a-shell/</link><pubDate>Tue, 06 Oct 2026 00:00:00 +0000</pubDate><guid>https://polymatx.dev/blog/posts/opsgate-ai-agents-without-a-shell/</guid><description>&lt;p&gt;I run my own server — nginx, Docker, a database, a handful of systemd units. Most of my day already happens in Claude Code, so the obvious next step was to point the agent at that server and let it answer questions like &amp;ldquo;what filled the disk?&amp;rdquo; or &amp;ldquo;why is nginx throwing 502s?&amp;rdquo; without me pasting logs into a chat window.&lt;/p&gt;
&lt;p&gt;Every option I found offered some version of the same deal:&lt;/p&gt;</description></item></channel></rss>