<?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/65522de49d094c71ba6953b813e5b0a6&quot; frameborder=&quot;0&quot; width=&quot;2100&quot; height=&quot;1575&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1575</height><width>2100</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1575</thumbnail_height><thumbnail_width>2100</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/65522de49d094c71ba6953b813e5b0a6-89c483a47aa41a65.gif</thumbnail_url><duration>136.466667</duration><title>Set Up PMB for Your AI Agent</title><description>This Loom explains how to set up PMB so an AI agent can remember and access your project automatically. It takes about two minutes: first install PMB using a single command (or an npx launcher if you do not have Python), then connect your agent so PMB is wired in through hooks and MCP. The same command can be used across Cursor, codecs, and several other tools by changing the name. The Loom also shows that the PMB dashboard lets you view a living graph of your project and the lessons it has picked up on your machine.</description></oembed>