NVIDIA Metropolis
NVIDIA Metropolis is a collection of models, libraries, and skills that provides everything you need to build, deploy, and scale video analytics AI agents and applications, from the edge to the cloud. You can now easily transform raw video and sensor data from real-world environments into real-time, actionable insights. This helps your organization understand what’s happening in your physical spaces and respond intelligently, while delivering exceptional scale, throughput, cost-effectiveness, and faster time to production.
How Metropolis Works
Metropolis offers a cohesive, end-to-end stack of software building blocks and agent skills that handle everything from video ingestion to insight generation to advanced agentic AI-powered analytics. These components can be deployed consistently across the whole compute spectrum—on the edge, in on-prem servers, or in the cloud—so the same applications can run close to where data is generated or centrally at scale.
Agentic Video Search at Scale With NVIDIA VSS Blueprint and Skills
Build custom visual AI agents in minutes with NVIDIA VSS skills. Explore new agentic skills, modular architecture, and reference workflows to turn videos into actionable insights.
Fine-Tune World Models With NVIDIA Cosmos Frameworks
Try an open source framework and skills for fine-tuning, distillation, inference acceleration, and deployment of vision AI models.
Solve the Training Data Challenge With Agentic Blueprints
Use agentic blueprints to quickly curate, label, and generate synthetic data for visual inspection or augment videos and images for specific events, attributes, or edge cases.
Get Started With Metropolis
Models That Power Visual AI Agents
NVIDIA Cosmos
Meet the first OmniModel that sees, reasons, generates many outcomes, and teaches physical agents how to act in the real world.
NVIDIA Nemotron™
Build powerful AI agents with efficient, open large language models for advanced reasoning, multimodal understanding, and complex workflows.
Try It Now
Embeddings
Turn images, videos, and text into vector representations for physical AI and multimodal understanding using NVIDIA models like Cosmos Embed, C-RADIO, and NV-CLIP.
NVIDIA Kumo
Turn connected business data into predictions, forecasts, and recommendations—without training a separate model for each task.
Frontier Models
Use leading AI models that enable advanced reasoning and understanding across text, images, and video.
Tools and Libraries to Build, Train, and Customize Your Agents
Cosmos Frameworks
Explore open source frameworks and skills for fine-tuning, distillation, inference acceleration, and deployment of vision AI models.
Cosmos Data Factory
Build a synthetic data generation pipeline with your own video or image data. Then, curate, augment, and evaluate it with Cosmos open models to accelerate vision AI model development.
Try Cosmos Data Factory Blueprints
Multi-Camera Tracking
Explore open source frameworks and skills for fine-tuning, distillation, inference acceleration, and deployment of vision AI models.
Learn MoreNeMo Switchyard
Route agent workloads across specialized and frontier models to balance performance, cost, and efficiency.
Try It NowStart developing vision AI applications with foundational Metropolis frameworks.
NVIDIA Metropolis Blueprint For Video Search and Summarization (VSS)
The VSS blueprint lets you build customizable video analytics AI agents to deliver powerful insights with seamless edge-to-cloud integration. VSS also brings skills to build these agents from simple natural language prompts using coding agents.
Try It Now
Factory Operations Blueprint
Build always-on manager agents that identify issues, adapt AI models, and coordinate action across specialized agents - turning fragmented operations data into action.
Apply for Early Access
NVIDIA Halos Outside-In Safety Blueprint
Extends robot perception using external cameras when building safety agents.
Starter Kits
Develop Video Analytics AI Agents
Build intelligent systems that can see, understand, and interact with the world through computer vision and real-time visual reasoning.
Build Agents for Smart City and Warehouse Operation
Explore examples for optimized VSS blueprint configuration with sample data, tailored prompts, and report templates.
Post-Train NVIDIA Cosmos 3
Boost accuracy for your use cases with LoRA and supervised Fine-tuning using NVIDIA Cosmos Framework
Generate Synthetic Data
Create synthetic images and videos to expand training datasets, reduce collection costs, and improve vision model robustness across diverse scenarios.
More Resources
Ethical AI
NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their supporting model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse.
For more detailed information on ethical considerations for this model, please see the Model Card++ Explainability, Bias, Safety & Security, and Privacy Subcards. Please report security vulnerabilities or NVIDIA AI Concerns here.
Develop, deploy, and scale AI-enabled video analytics applications with
NVIDIA Metropolis.