<?xml version="1.0" encoding="UTF-8"?><oembed><type>video</type><version>1.0</version><html>&lt;iframe src=&quot;https://www.loom.com/embed/3fa0852fd38c40029a89080944662bbf&quot; frameborder=&quot;0&quot; width=&quot;1920&quot; height=&quot;1440&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1440</height><width>1920</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1440</thumbnail_height><thumbnail_width>1920</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/3fa0852fd38c40029a89080944662bbf-5ae32c13c6cde5af.gif</thumbnail_url><duration>43.166667</duration><title>Own Your AI Locally, Forever</title><description>This Loom explains an offline AI setup that eliminates reliance on third party servers. It claims that without internet connectivity, other AI tools lose functionality, but this solution quietly changes that by letting you pay once and run models locally, from 1 to 100 billion parameters powered by llama.cpp and Air LLM. It describes an all in one companion with a built in AI chat, asking anything, and a complete IDE with Monaco Editor, a built in terminal, and AI suggestions. The pitch includes a lifetime license and availability now, with the AI running on your machine and under your rules.</description></oembed>