<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>LLM on Unbound Force</title><link>https://unboundforce.dev/tags/llm/</link><description>Recent content in LLM on Unbound Force</description><generator>Hugo</generator><language>en-US</language><copyright>Copyright (c) 2025-2026 Unbound Force</copyright><lastBuildDate>Sun, 23 Aug 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://unboundforce.dev/tags/llm/index.xml" rel="self" type="application/rss+xml"/><item><title>Dewey Goes Cloud-Optional — Pluggable LLM Providers for Embedding and Synthesis</title><link>https://unboundforce.dev/blog/pluggable-llm-providers/</link><pubDate>Sun, 23 Aug 2026 00:00:00 +0000</pubDate><guid>https://unboundforce.dev/blog/pluggable-llm-providers/</guid><description>&lt;h2 id="the-problem-with-local-only"&gt;The Problem with Local-Only&lt;/h2&gt;
&lt;p&gt;Dewey started as a local-first knowledge system. Ollama handled both embedding and synthesis, which meant zero cloud dependencies and full data sovereignty. That design worked — until it didn&amp;rsquo;t.&lt;/p&gt;</description></item></channel></rss>