1. [Industries](/industries/overview) 2. Public Sector # Developer Resources for the Public Sector NVIDIA technologies for use cases across agentic AI, open source, digital twins, and remote sensing. Use Cases: - Agentic AI - Open Source - Robotics and Autonomy - Simulation and Training - Remote Sensing ## Get Started With Public Sector Use Cases Agentic AI Open Source Robotics and Autonomy Simulation and Training Remote Sensing **Blueprint** ### Autonomous Orchestration of Agentic Workflows Federal agencies are automating the extraction and synthesis of insights from multimodal enterprise data to deliver real-time situational awareness and faster, more informed decision-making. Autonomous workflows enhance productivity with critical information advantages and reduce cognitive load. [Build an Enterprise RAG Pipeline Blueprint](https://build.nvidia.com/nvidia/build-an-enterprise-rag-pipeline) **Blueprint** ### Agentic AI Automation in Public Services Agentic AI is being used to automate administrative tasks, summarize documents, and improve internal communications, accelerating decision-making and streamlining service delivery. AI tools enable agencies to personalize content and citizen interactions, resulting in more engaging and responsive public services. [Explore NVIDIA AI-Q for Intelligent Agents](https://build.nvidia.com/nvidia/aiq) **Blueprint** ### Building Agentic AI Applications with LLMs Federal agencies are deploying and optimizing AI agents for more efficient government operations. Learn how to design intelligent agents that can be adapted for arbitrary environments at scale. Utilizing frameworks like LangGraph and NVIDIA NIM, you'll build agents capable of deep thought, long-horizon reasoning, content management, and real-time operations. [Enroll in the DLI Course](https://learn.nvidia.com/courses/course-detail?course_id=course-v1:DLI+C-FX-25+V1) **Blueprint** ### Run Always-on Agents With Greater Control and Privacy NVIDIA NemoClaw™ for OpenClaw is an open source reference stack that simplifies running always-on assistants with a single command. It installs the NVIDIA OpenShell™ runtime to add policy-based privacy and security guardrails, giving users more control over their agents' behavior and data handling. [Explore NVIDIA NemoClaw for OpenClaw](https://build.nvidia.com/nvidia/nemoclaw-for-openclaw/nemoclawcard) **Blueprint** ### Deploy an Adaptive Agent Experience NemoClaw for Hermes Agents is an open source blueprint for running autonomous agents in enterprise environments. This blueprint helps teams deploy Hermes agents that work with approved tools and data sources, learn preferred workflows from real usage, and turn repeatable guidance into durable skills. [Explore NemoClaw for Hermes Agents](https://build.nvidia.com/nvidia/nemoclaw-for-hermes-agent/nemoclawcard) **Blueprint** ### Building Real-Time Voice Agents In this developer example, explore a comprehensive, end-to-end voice agent blueprint built with NVIDIA Nemotron state-of-the-art open models. It guides developers through the creation of a cascaded pipeline, integrating Nemotron automatic speech recognition, large language model, and text-to-speech, while solving for the complexities of streaming, interruptible conversations. [Explore Nemotron for Voice Agents](https://build.nvidia.com/nvidia/nemotron-voice-agent) **Blueprint** ### Synthetic Manipulation Motion Generation for Robotics Autonomous vehicles and robotics are enhancing operations, improving safety, and increasing efficiency in complex and changing environments. By using simulation-driven development and edge AI processing, agencies can streamline logistics, manufacturing, and service delivery with minimal risk and greater adaptability. [Explore the NVIDIA AI Blueprint](https://build.nvidia.com/nvidia/isaac-gr00t-synthetic-manipulation) **Training** ### Scalable Multi-Robot Scene Workflows Using ROS Simulation Interfaces Standard in Isaac Sim In this lab, you'll learn to orchestrate multi-robot collaboration, automate workflows, and execute autonomous navigation and object manipulation tasks in a test warehouse scenario using ROS 2, Simulation Interfaces, and Isaac Sim™. [Explore the Training Lab](https://docs.nvidia.com/learning/physical-ai/going-further-with-robotics/latest/scalable-multi-robot-scene-workflows-using-ros-simulation-interfaces-standard-in-isaac-sim/index.html) **Training** ### Synthetic Data Generation for Perception Model Training in Isaac Sim In this module, we'll delve into the fundamentals of perception models, synthetic data generation, and how to apply these concepts to real-world robotic applications. Throughout this module, we'll take a hands-on approach to learning, guiding you through the process of designing a simulated environment, generating synthetic data, training an AI perception model, and integrating it into a robotic workflow. [Explore the Training Module](https://docs.nvidia.com/learning/physical-ai/getting-started-with-isaac-sim/latest/synthetic-data-generation-for-perception-model-training-in-isaac-sim/index.html) **Blueprint** ### NVIDIA Omniverse DSX Blueprint for AI Factory Digital Twins The NVIDIA Omniverse™ DSX Blueprint is the digital twin manifestation of the DSX reference design, demonstrating to developers how to use Omniverse libraries for design, simulation, and operations across AI factory facilities and their hardware–software ecosystem. [Explore the NVIDIA AI Blueprint](https://build.nvidia.com/nvidia/omniverse-dsx-blueprint-for-ai-factories) **Blueprint** ### Enhance Predictive Maintenance Accelerated data processing and efficient ETL workflows enable predictive maintenance for faster, smarter decisions and lower costs. The optical inspection of public infrastructure is critical in accelerating time to insight and improving the assessment of maintenance needs. [Learn How to Build a Video Search and Summarization (VSS) Agent](https://build.nvidia.com/nvidia/video-search-and-summarization) **Training** ### Extend Omniverse Kit Applications for Building Digital Twins In this hands-on course, you'll learn how to develop OpenUSD-based digital twin applications on the Omniverse platform, focusing on data aggregation, interactivity, and physics simulation. [Enroll in the DLI Course](https://learn.nvidia.com/courses/course-detail?course_id=course-v1:DLI+S-OV-13+V1) **Blueprint** ### Visualization and Simulation of Geospatial Environments GPU-accelerated pipelines in the cloud rapidly process massive satellite and sensor data, enabling faster, more informed decisions for geospatial intelligence. These advanced AI and computer vision workflows enhance visualization and simulation for digital twins, autonomous systems, sensor processing, and more. [Explore AI Weather Analytics With Earth-2](https://build.nvidia.com/nvidia/earth2-weather-analytics) **Blueprint** ### Air Traffic Management Systems Accelerated Signal Processing Accelerated radar and signal processing enables real-time analysis in air traffic management. These enhancing signal processing frameworks equip controllers with the timely, detailed insights needed to manage complex and ever-increasing traffic volumes. [Learn How to Build a Digital Twin for Interactive Fluid Simulation](https://build.nvidia.com/nvidia/digital-twins-for-fluid-simulation) **Training** ### Disaster Risk Monitoring Using Satellite Imagery Learn how to build and deploy a deep learning model to automate the detection of flood events using satellite imagery. This workflow can be applied to lower the cost, improve the efficiency, and significantly enhance the effectiveness of various natural disaster management use cases. [Enroll in the DLI Course](https://learn.nvidia.com/courses/course-detail?course_id=course-v1:DLI+S-ES-01+V1) ## Explore Tools and Technologies for Public Sector **NVIDIA NeMo** ### Accelerate Specialized AI Agent Optimization NVIDIA NeMo is an agent-first, open suite of libraries with skills for accelerating AI agent specialization, optimization, and governance. NeMo integrates with existing AI tools and agent frameworks to optimize specialized agents across any cloud, on-premises, or hybrid environment. [Get Started With NeMo](https://www.nvidia.com/en-us/ai-data-science/products/nemo/) **NVIDIA Omniverse** ### Create Physically Accurate World-Scale Simulations NVIDIA Omniverse libraries include open-source and accelerated tools for agents and software developers to integrate prebuilt physical AI simulation capabilities into their applications and services. Agents can call on these capabilities as tools, while Omniverse skills help orchestrate agentic workflows across simulation pipelines. [Get Started With Omniverse](/nvidia-omniverse-platform) **NVIDIA Holoscan** ### Enhance High-Compute Applications NVIDIA Holoscan is a domain-agnostic, multimodal AI sensor processing platform that provides the accelerated, full-stack infrastructure needed for real-time processing of streaming data at the edge or in the cloud. [Get Started With Holoscan](/holoscan-sdk) **NVIDIA Isaac Sim** ### Advance AI Robotic Development NVIDIA Isaac Sim is an open source reference framework built on NVIDIA Omniverse libraries for robotics simulation, testing, and synthetic data generation in physically based virtual environments. [Get Started With Isaac Sim](/isaac/sim) **NVIDIA Metropolis** ### Build, Deploy, and Scale Vision AI Agents and Applications NVIDIA Metropolis is a collection of models, libraries, and blueprints 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. [Get Started With Metropolis](/metropolis) **NVIDIA DeepStream** ### Drive Vision AI Development With Agents NVIDIA DeepStream's multi-platform support gives you a faster, easier way to develop and deploy real-time video streaming pipelines for generative AI agents and applications. You can even deploy them on premises, at the edge, and in the cloud with just the click of a button. [Get Started With DeepStream](/deepstream-sdk) ## Browse by Resource Type Sessions Blogs ## More Resources ![Decorative image representing Developer Community](https://developer.download.nvidia.com/icons/m48-developer-1.svg) ### Join the NVIDIA Developer Program ![Decorative image representing Training and Certification](https://developer.download.nvidia.com/icons/m48-certification-ribbon-2.svg) ### Get Training and Certification ![Decorative image representing Inception for Startups](https://developer.download.nvidia.com/images/isaac/m48-ai-startup-256px-blk.png) ### Accelerate Your Startup