Nemotron Labs

What if you could talk to your computer and have it perform tasks through the Bash terminal—without writing a single command? With NVIDIA  Nemotron, you can build a natural‑language Bash agent from scratch in under an hour, with about 200 lines of Python and minimal dependencies.

Curious how it works? Join us for a developer‑focused livestream that takes you from first principles to running code, exploring the “why” and “how” of building agentic AI through hands‑on examples.

We’ll cover, step by step:

• A live demo: building and running a Bash computer use agent in real time with Nemotron, NVIDIA’s open reasoning model
• How to connect tools, use memory, and safely enable human‑in‑the‑loop command execution
• A bonus look at how LangGraph simplifies orchestration and workflow design
• Your questions, answered live—with explanations and no prior AI agent experience needed

By the end, you’ll understand how modern AI agents think, plan, and act in code—and leave with reusable Python you can adapt to your own projects. Bring your curiosity and get ready to learn by doing!

Join us on: YouTube, LinkedIn, X

Got questions about Nemotron? Want to give direct feedback to the team behind the models?

Ask our Nemotron expert in this Nemotron Lab office hours about:

• Our Nemotron open model family with open datasets and open techniques and share your ideas
• How to build AI agents, including report generator agent, RAG agent, and bash computer use agent from our recent tutorial livestreams
• Nemotron Summit at NeurIPS Conference (Mon, Dec 1 4-8pm PT) for AI model builders and researchers 

This is your chance to get hands-on support, ask questions, and explore the Nemotron models with the experts who built them. Whether you’re just starting your AI journey or you’re ready to dive deeper, this stream is for you!

RSVP to join the office hours and drop your questions in our Discord channel or in the comments below.