<?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[OpenPlayground - multi-AI / GPT interface]]></title><description><![CDATA[<ul>
<li><a href="https://github.com/nat/openplayground" target="_blank" rel="noopener noreferrer nofollow ugc">https://github.com/nat/openplayground</a></li>
<li><a href="https://nat.dev" target="_blank" rel="noopener noreferrer nofollow ugc">https://nat.dev</a> (demo)</li>
<li><a href="https://twitter.com/natfriedman/status/1643097101235269633" target="_blank" rel="noopener noreferrer nofollow ugc">https://twitter.com/natfriedman/status/1643097101235269633</a></li>
</ul>
<blockquote>
<h1>openplayground</h1>
<p dir="auto">An LLM playground you can run on your laptop.</p>
<h4>Features</h4>
<ul>
<li>Use any model from <a>OpenAI</a>, <a>Anthropic</a>, <a>Cohere</a>, <a>Forefront</a>, <a>HuggingFace</a>, <a>Aleph Alpha</a>, and <a>llama.cpp</a>.</li>
<li>Full playground UI, including history, parameter tuning, keyboard shortcuts, and logprops.</li>
<li>Compare models side-by-side with the same prompt, individually tune model parameters, and retry with different paramaters.</li>
<li>Automatically detects local models in your HuggingFace cache, and lets you install new ones.</li>
<li>Works OK on your phone.</li>
<li>Probably won't kill everyone.</li>
</ul>
</blockquote>
<p dir="auto"><img src="/assets/uploads/files/1680624076156-d75e69cf-df47-45e2-92ec-1d98cf94d42a-image-resized.png" alt="d75e69cf-df47-45e2-92ec-1d98cf94d42a-image.png" class=" img-fluid img-markdown" /></p>
]]></description><link>https://forum.cloudron.io/topic/8955/openplayground-multi-ai-gpt-interface</link><generator>RSS for Node</generator><lastBuildDate>Wed, 16 Sep 2026 13:05:23 GMT</lastBuildDate><atom:link href="https://forum.cloudron.io/topic/8955.rss" rel="self" type="application/rss+xml"/><pubDate>Tue, 04 Apr 2023 16:06:46 GMT</pubDate><ttl>60</ttl></channel></rss>