<?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/fdb1c1d2472b47c0b98fbb803348c8b4&quot; frameborder=&quot;0&quot; width=&quot;1114&quot; height=&quot;835&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>835</height><width>1114</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>835</thumbnail_height><thumbnail_width>1114</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/fdb1c1d2472b47c0b98fbb803348c8b4-771d3878c0481a7f.gif</thumbnail_url><duration>339.32</duration><title>Real-Time Collaboration Between Claude Instances Using Cross-Claude MCP</title><description>In this video, I demonstrated how two separate cloud instances, Claude.ai and Claude Code, can collaborate in real time using a shared message bus called Cross Claude. I walked through the process of registering both instances, sending code for review, and implementing fixes identified by cloud.ai. This seamless interaction showcases the potential for multiple Claude platforms and instances to communicate and work together, regardless of their location or the devices being used. I encourage you to explore this open-source solution, which is free and available via</description></oembed>