video-agent

NVIDIA AI Blueprint for video search and summarization (VSS) is a GPU-accelerated reference architecture for building video analytics agents with real-time verified alerts, visual Q&A, and automated reporting. The VSS Blueprint uses vision language models (VLMs) such as NVIDIA Cosmos, LLMs such as NVIDIA Nemotron, RAG, and NVIDIA NIMs.

Official Implementation of "Visual Agentic Memory: Online Long Video Understanding via Online Indexing, Hierarchical Memory, and Agentic Retrieval"