<?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/3113e6a733624b91b0056f823226e321&quot; frameborder=&quot;0&quot; width=&quot;1112&quot; height=&quot;834&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>834</height><width>1112</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>834</thumbnail_height><thumbnail_width>1112</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/3113e6a733624b91b0056f823226e321-a977a314f90911fc.gif</thumbnail_url><duration>146.221</duration><title>Introducing NEMOS: The AI Memory Layer for Enhanced LLMs 🚀</title><description>Hey everyone, I&apos;m Brayden Stitt, and I&apos;m excited to share my project called NEMOS, which is an AI memory layer designed to enhance various LLM offerings. I&apos;ve developed a Chrome extension that allows users to inject memory into different LLMs, utilizing GPT-5 for filtering relevant memories and Pinecone for our vector database. During the demo, I showed how the system can store and retrieve user preferences, like favorite candy and movies. I encourage you to check out the functionality and see how it can improve your interactions with LLMs. Let me know what you think!</description></oembed>