Main Calendar

Starting with JetPack 7.2, NVIDIA officially supports the Yocto Project on Jetson. But the story began years earlier with meta-tegra, the community project created and maintained by Matt Madison that brought Yocto Project to Jetson and became a trusted foundation for embedded Linux developers.

Join Matt Madison and NVIDIA experts as they discuss the origins of meta-tegra, the journey from community-driven project to official NVIDIA support, and what this milestone means for developers building products with Jetson.

What you'll learn:

• The origin of meta-tegra and the problem it was built to solve
• What NVIDIA's commitment to OE4T means in practice for the codebase and community
• Whether the Yocto Project is right for your Jetson product—and how to get started

Join us live, bring your questions, and hear the story directly from the people who built it.

NVIDIA Alpamayo 2 Super is here — a 32-billion-parameter open reasoning VLA model that doesn't just drive, it reasons, plans, and acts across the full autonomous vehicle stack. In this livestream, NVIDIA experts will share how the full Alpamayo platform — including AlpaGym and the Physical AI Dataset — closes the loop from real-world data to in-vehicle deployment. If you're working on robotaxis or L4 enabled autonomy, this is the livestream you won’t want to miss.

Top 3 things attendees will learn:

• What's new in Alpamayo 2 Super — including the jump to 32B parameters, full 360-degree surround perception, and Meta-Action outputs — and why it matters.
• How AlpaGym's closed-loop reinforcement learning framework trains models on the consequences of their driving decisions, before they ever touch a real road.
• How to go from real-world fleet data to in-vehicle inference on DRIVE AGX Thor using distillation recipes — with live demos of the full pipeline.

オープンモデルやオープンエージェントを使うことで、推論し、ツールを呼び出し、継続的に動作する AI エージェントを自作しやすくなっています。一方で次に重要になるのは、そのエージェントを現実のツールやシステムにつなぐときに、どこで安全性を確保するかです。

この Nemotron Labs ライブストリームでは、クラスメソッド社 森茂 洋氏をゲストに迎え、NVIDIA Nemotron、OpenClaw、NVIDIA OpenShell と組み合わせて、安全な AI エージェント開発を始めるための入口として NVIDIA NemoClaw を紹介します。NemoClaw、OpenShell、OpenClaw がそれぞれどこで動き、サンドボックスやポリシー制御がどこで効くのかを整理しながら、エージェントをツール、API、ドメイン固有のワークフローにつなぐ際の考え方を解説します。

この回では、以下を取り上げます。

• NemoClaw、OpenShell、Nemotron、OpenClaw それぞれの役割と連携のしくみ
• 長時間動作するエージェントに sandbox、network policy、tool boundary が必要な理由
• 単なるチャットアシスタントを超えた Build-a-Claw の実践的な流れ
• NVIDIA の agent skills 事例から見る、open agent を実システムにつなぐための発展形

AI エージェントを「試す」段階から、オープンモデル、オープンエージェント、制御された実行環境を使って「より安全に自作する」段階へ進むための入門です。

Welcome and Training Lab Setup 

Introductions and check access, environment assumptions, and the agent-first goals for Isaac for Healthcare
Speaker: Mostafa Toloui 

Isaac for Healthcare Overview

See how the Rheo blueprint within Isaac for Healthcare leverages agent-ready, skill-based development for hospital automation scenarios. Understand how Project Rheo turns hospital spaces and workflows into sim-ready, trainable digital environments.
Speaker: Mostafa Toloui 

Hands-on Lab

Set up the simulation environment, import robot and rigging, perform data collection/multiplication/augmentation, implement policy training
Speaker: Maximilian Ofir 

NVIDIA Spark Hack Toronto brought developers together for a weekend challenge: build an agentic application that runs locally on DGX Spark using open models and Toronto Open Data. Teams tackled everything from small business forecasting and dementia care to city-scale traffic simulation — all on an ASUS Ascent GX10 powered by the NVIDIA GB10 Grace Blackwell Superchip.
Cracked City took home Best Use of Nemotron for turning road and sidewalk damage reporting into a single step. Upload a photo, and their system analyzes the damage, estimates severity, and auto-generates a Toronto 311 report using image analysis, speech recognition, and NVIDIA Nemotron — all running locally on DGX Spark. 
Join us live to see a demo and chat with the winners. Bring your questions about building with Nemotron and local AI compute.

Welcome and Training Lab Setup 

Introductions and check access, environment assumptions, and the agent-first goals for Isaac for Healthcare
Speaker: Mostafa Toloui 

Isaac for Healthcare Overview

See how the Rheo blueprint within Isaac for Healthcare leverages agent-ready, skill-based development for hospital automation scenarios. Understand how Project Rheo turns hospital spaces and workflows into sim-ready, trainable digital environments.
Speaker: Mostafa Toloui 

Hands-on Lab

Set up the simulation environment, import robot and rigging, perform data collection/multiplication/augmentation, implement policy training
Speaker: Maximilian Ofir 

単に質問に答えるだけでなく、研究業務を支援する AI エージェントを作るには何が必要でしょうか。Research がもっと手軽に、速く、再現性高く行えるようになると、研究者、エンジニア、ソリューションアーキテクト、フィールドチームの現場では何が変わるのでしょうか。

本 Nemotron Labs ライブストリームでは、Kenji Tanaka と Microsoft の Hisaho Nakata 氏が、研究者代理 AI を AI for Science やエンタープライズの技術検証ワークフローにどう活用できるかを考えます。調査計画、ツール利用、根拠整理、技術選択肢の比較、リサーチブリーフや検証計画、次アクション作成まで、散らばった情報を実践的なアウトプットに変える流れを扱います。

Research が手軽になることは、重複調査の削減、PoC 計画の高速化、ナレッジ共有の改善、根拠に基づく意思決定につながります。また、その場限りの調査を、再利用できるブリーフ、チェックリスト、アクションプランとして残しやすくなります。

このライブストリームでは、以下を取り上げます。

- NVIDIA NemoClaw、NVIDIA OpenShell, OpenClaw が、長時間動作する研究者代理 AI の土台としてどう連携するか
- 研究者代理 AI が、単なるチャットから、計画、調査、ツール利用、構造化されたアウトプットへどう発展するか
- NVIDIA DGX Spark、Azure、Microsoft AI for Science のワークフローを Agentic AI パターンにどう接続できるか
- 実際の研究データや企業データに適用する前に確認すべき、セキュリティ、データアクセス、情報源の品質、監査性の論点

研究者代理 AI が、現場の調査を速くし、技術判断を助け、AI for Science のアイデアを実装に近づける方法を紹介します。

NVIDIA Spark Hack Toronto brought developers together for a weekend challenge: build an agentic application that runs locally on DGX Spark using open models and Toronto Open Data. Teams tackled everything from small business forecasting and dementia care to city-scale traffic simulation — all on an ASUS Ascent GX10 powered by the NVIDIA GB10 Grace Blackwell Superchip.

Belong won the Public Services track with an AI companion designed for people living with dementia and their caregivers. Running entirely on DGX Spark, it helps users recognize family members, remember appointments, and find local services — keeping all conversations and memory data on-device using Nemotron, speech, and retrieval systems.

CityFlow won the Economic Systems track with a real-time intelligence platform for small businesses. By combining transit disruptions, road closures, weather, events, and other Toronto data sources, it helps business owners answer practical questions like "Am I properly staffed for Friday night?" — using Nemotron to generate recommendations and NVIDIA cuOpt to turn forecasts into actual staffing plans.

Join us live to see demos and chat with both teams. Bring your questions about building with local AI compute and Toronto Open Data.

Hear from NVIDIA CEO Jensen Huang live on stage at the iconic Tempodrom. Arrive early to catch the GTC Live pregame show for an insightful discussion on the latest in AI infrastructure with industry leaders.