Build Claw Agents on Jetson | NVIDIA Jetson AI Lab

Take the leap from local models to local agents. In this session, developers learn how to move beyond running a model and deploy a fully autonomous AI assistant on NVIDIA Jetson — no cloud required. OpenClaw provides a local AI assistant framework that connects to chat interfaces, browser-based tools, and multi-step agentic tasks. NemoClaw extends that baseline with sandboxing, inference routing, and policy controls for safer, production-ready edge deployments.

In this stream, you will learn how to move from running a local model to running a fully local autonomous agent on NVIDIA Jetson.

We'll cover:

• Building a local assistant with OpenClaw — build a full local assistant architecture that connects to chat workflows, browser-based tools, and multi-step tasks — running privately on your own hardware, 24/7.
• Why tool-calling models matter — see what changes when an AI system can take actions, use tools, and run autonomously, and what breaks when your model can't do it reliably.
• Safer local agents with NemoClaw — go further with sandboxing, onboarding, inference routing, and policy controls that make local agent deployment more structured and production-ready.
• Real-world use cases — explore what becomes possible: building dynamic browser-based games, prototyping smart computer vision apps, and running long research tasks without any cloud dependency.