<?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/760aca16a006429cb5bafe49f22d96f6&quot; frameborder=&quot;0&quot; width=&quot;1110&quot; height=&quot;832&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>832</height><width>1110</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>832</thumbnail_height><thumbnail_width>1110</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/760aca16a006429cb5bafe49f22d96f6-fa0bf47632ff760a.gif</thumbnail_url><duration>226.8604</duration><title>Solving the Cold Start Problem in Personal Agents with OpenMnesia 🚀</title><description>Hey everyone, I&apos;m excited to introduce OpenMnesia, which addresses the cold start problem for personal agents by continuously feeding memory into them. Our SDK, which can run locally or on services like Akash, captures data from various sources like iMessage and code repositories, building a SQLite database that enriches this information. We extract skills and patterns from your interactions, allowing for the creation of markdown or JSON files that can be integrated with other tools. I encourage you to explore the different ingestion methods and see how we can enhance your personal agent experience. Let&apos;s leverage this technology to streamline our workflows!</description></oembed>