Twelve Labs unveils a video intelligence stack built around search, memory and agentic workflows

qdrant_engine · x · 2026-07-29

Twelve Labs explains why video cannot be treated as just a bag of frames or a timestamped transcript: motion, causality, and temporal progression matter. At Vector Space Day SF, James Le described three failure modes in video systems — wrong context, wrong memory, and wrong reasoning — and introduced a stack built around Marengo for video search, Pegasus for structured answers, and Jockey as an agentic framework and memory layer, with Qdrant underneath for storage and retrieval.

Original post →

More from coding & agent

coding & agent channel →