<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Homelab on Kerman's Blog</title><link>/tags/homelab/</link><description>Recent content in Homelab on Kerman's Blog</description><generator>Hugo -- gohugo.io</generator><language>en</language><managingEditor>kermansanjuanmalax@gmail.com (Kerman Sanjuan Malax-Echevarria)</managingEditor><webMaster>kermansanjuanmalax@gmail.com (Kerman Sanjuan Malax-Echevarria)</webMaster><copyright>© 2026 Kerman Sanjuan Malax-Echevarria</copyright><lastBuildDate>Mon, 24 Aug 2026 00:00:00 +0000</lastBuildDate><atom:link href="/tags/homelab/index.xml" rel="self" type="application/rss+xml"/><item><title>self-hosting honcho with a local gpu in an lxc on proxmox</title><link>/posts/self-hosting-honcho-gpu-lxc-proxmox/</link><pubDate>Mon, 24 Aug 2026 00:00:00 +0000</pubDate><author>kermansanjuanmalax@gmail.com (Kerman Sanjuan Malax-Echevarria)</author><guid>/posts/self-hosting-honcho-gpu-lxc-proxmox/</guid><description>Running Honcho, the memory server for agents, on a self-hosted Proxmox LXC with a local GPU powering the embeddings. No cloud, no per-token memory cost, and the full reasoning stack kept private.</description></item></channel></rss>