<?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/93d9a311d969460ba74cd2bb861e9a75&quot; frameborder=&quot;0&quot; width=&quot;1670&quot; height=&quot;1252&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1252</height><width>1670</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1252</thumbnail_height><thumbnail_width>1670</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/93d9a311d969460ba74cd2bb861e9a75-80e24a1ba75319cc.gif</thumbnail_url><duration>1231.311</duration><title>Memory in Claude Cowork</title><description>In this video, I demonstrate how to set up memory and instructions in CloudCowork, which is also applicable to CloudCode and OpenAI&apos;s Codex. I walk you through creating a Claude.md file that contains essential instructions for the workspace and a memory.md file for additional context. I emphasize the importance of keeping the Claude.md concise while using the memory.md for more nuanced information. I also show how to link these files so that Claude can access the memory effectively. Please take note of these steps and consider implementing this setup in your own projects.</description></oembed>