Jockey by TwelveLabs

Jockey is the first AI that understands your entire media library just like you do, searching by person, moment, or context across every photo and video you've captured, built on TwelveLabs' advanced model stack (Marengo and Pegasus) that improves automatically with every update. This isn't another tagging tool; Jockey actually comprehends what happens inside a video, not just the labels on a segment — moving from “AI writes a description a human has to read” to “AI emits structured data you can query.”

Describe a moment in plain language and Jockey finds the exact clip, not the folder. Search everything you've ever said on camera and jump straight to the line. For marketing teams, every ad is automatically labeled by hook, talent, format, and tone the moment it lands, and Jockey identifies which opening three seconds actually hold attention across your whole library. It works through the assistants you already use — connect via MCP for Claude now, ChatGPT coming soon — or build custom applications with the API, so there's no new workflow to adopt.

When you delete your library or account, your original files, the generated index, associated metadata, and usage history are permanently removed. Pricing is tiered by how much media you store, and every plan runs the full Marengo + Pegasus engine.