<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0"><channel><title><![CDATA[AFFiNE - use local LLM?]]></title><description><![CDATA[<p dir="auto">Hello</p>
<p dir="auto">I tried installing AFFiNE, and it looks like it works well. However, I am struggling to install/set up AFFiNE with a local LLM provider.</p>
<p dir="auto">Context: My backend is a Mac (not the Cloudron server) that runs a local LLM (via KoboldCPP), and other Cloudron apps (++) can access this perfectly well via the LAN IP. Not so with AFFiNE. For some reason, I first struggled to get anything other than error messages, and now, I get the following error message:</p>
<pre><code>You've reached the current usage cap for AFFiNE AI. You can subscribe to AFFiNE AI(with free 7-day-trial) to continue the AI experience!
</code></pre>
<p dir="auto">This error message persists even if I followed AI advice to set the env variable to self hosted:</p>
<pre><code>cloudron env set selfhosted=true
</code></pre>
<p dir="auto">Has anyone successfully set up AFFiNE with a local LLM, like my setup? Anyone have any advice for me?</p>
]]></description><link>https://forum.cloudron.io/topic/16006/affine-use-local-llm</link><generator>RSS for Node</generator><lastBuildDate>Wed, 30 Sep 2026 12:26:17 GMT</lastBuildDate><atom:link href="https://forum.cloudron.io/topic/16006.rss" rel="self" type="application/rss+xml"/><pubDate>Thu, 24 Sep 2026 12:16:33 GMT</pubDate><ttl>60</ttl></channel></rss>