Get Started With NVIDIA Metropolis Microservices for Jetson


Release Highlights

NVIDIA Metropolis microservices for Jetson gives you a collection of powerful cloud-native microservices and building blocks to build end-to-end vision AI applications for the edge powered by NVIDIA Jetson™. Elevate your application by seamlessly integrating generative AI capabilities and future-proof your solutions through a sophisticated blend of microservices, providing an API-driven, modular, and highly extensible framework.

This latest release of NVIDIA Metropolis microservices for Jetson features:


  • Two reference applications—AI-NVR and zero-shot detection using generative AI
  • 15+ microservices, including application and platform services
  • Full-featured media management and storage microservices
  • Core platform services like IoT Gateway, API Gateway, monitoring, and unified system bus
  • Cloud microservices for login, authentication, and secure invocation of device APIs
  • Multi-stream AI perception with dynamic stream discovery and addition
  • An analytics microservice for understanding people and object movement through physical spaces

For more information about how to get started, refer to the Quick Start Guide


By downloading or using the software and materials, you agree to the License Agreement for NVIDIA Metropolis Microservices Evaluation .




Featured Resources

Technical Whitepaper

Dive into a comprehensive overview of Metropolis microservices for Jetson.

Read the Whitepaper

Blog: Bringing Generative AI to the Edge

Learn how to bring generative AI applications into production faster with Metropolis Microservices for Jetson.

Read the Blog Watch the Demo

Blog: Build Vision AI Applications with APIs

Learn how to build vision AI applications using APIs provided by Metropolis Microservices for Jetson.

Read the Blog

Get Started Video Tutorial



Ethical AI

NVIDIA’s platforms and application frameworks enable developers to build a wide array of AI applications. Consider potential algorithmic bias when choosing or creating the models being deployed. Work with the model’s developer to ensure that it meets the requirements for the relevant industry and use case; that the necessary instruction and documentation are provided to understand error rates, confidence intervals, and results; and that the model is being used under the conditions and in the manner intended.