{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/f0473b8950a84fbdbacfe03f11f0344d\" frameborder=\"0\" width=\"1920\" height=\"1440\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1440,"width":1920,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1440,"thumbnail_width":1920,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/f0473b8950a84fbdbacfe03f11f0344d-b765d59eceff5506.gif","duration":80.256,"title":"MeZero Enables Persistent Personal Agent Context","description":"This Loom introduces MeZero, a plugin designed to make AI agents useful by providing persistent personal context. The speaker notes that while agents can offer superpowers, they become “dumb” without context, and setting up and managing that context across many agents like Codex and various platforms is time consuming. MeZero connects to Asian hard disks to build a personal context graph and uses one-click deployment with Atlassian and MongoDB to enable a private context instance. It then lets users create an MCP agent plugin across agents such as Claude, Code, Hermes, and Pi to deliver a hyper-personalized context layer."}