Your agent got the right answer. How much work did it take to get there?
We worked with @NousResearch/@Teknium on a hands-on walkthrough of NVIDIA NeMo Relay to collect traces for Hermes Agent. Run two example scenarios, follow the agent’s calls and retries, and see the full trace in Arize Phoenix.
The blog also looks at how Nous used traces and task results to evaluate fixes across repeated runs.
TechBlog: https://t.co/a0NtNvs9X3
📽️ by our own @Picomoorhead:
Big day today. 4 things. We celebrated @Picomoorhead getting engaged (she said yes), graduation, new job and his fiancée getting a job. Of course we had @nvidia cookies!
My first NVIDIA Blog is live! 👇 🦞
How to build a secure, always-on local AI agent on NVIDIA DGX Spark — using NemoClaw, OpenClaw, and Nemotron 3 Super 120B, with Telegram for remote access.
Everything runs on-device. OpenShell handles the sandboxing. The video walks through the full deployment end-to-end.
Blog: https://t.co/4QjN4TQcgY
Video: https://t.co/VghdDE3kos