Kris Murphy

Senior Product Manager @NVIDIA • Focused on Agentic AI software • Product Lead for NemoClaw • What are you building with Agents? • views are my own

[Kris Murphy @KrisMMurph]

@mazeyar Same :-)

[Teknium 🪽 @Teknium]

Hermes Agent is now dramatically more efficient, especially for smaller/weaker/local models!

With the help of @nvidia's Nemo Relay and several other strategies Hermes was able to identify a ton of optimizations beyond just saving tool execution time or memory - but also turns needed to complete tasks, schema improvements to reduce context load, and token efficiency gains by tracing through wasted turns and tool errors across all 250,000 conversations I've had with my Hermes.

All of the below are now in Hermes Agent, update to start saving now or wait until tomorrow for the full version update release.

[LangChain @LangChain]

Introducing the NemoClaw Deep Agents Blueprint, a reference architecture for building open agent systems developed with @NVIDIA

✅ A fully open stack enterprises can own and customize
✅ Benchmark-leading performance
✅ Over 10x lower inference costs

Blog: https://t.co/9QumeM3897

Video: https://t.co/KmTKS8r2fk

[Chris 🇨🇦 @llm_wizard]

"LLMs are mismanaged geniuses" is a common sentiment these days.

Basically: We're not even scratching the surface of current model intelligence because we don't know how to harness them most effectively.

But we know that harnesses will be like the operating systems of future companies.

LangChain - the absolute legends - are doing great work to try and start managing our geniuses a little bit better.

It's incredible to see the lift they got with Nemotron 3 Ultra from their work, and this is only just starting to scratch the surface!

[Kris Murphy @KrisMMurph]

@llm_wizard You may have caught me that I am just a bit fussy and like the fancy coffee :-)

[NVIDIA AI @NVIDIAAI]

Teach an agent a workflow once. Have it remember after every rebuild.

This tutorial shows how to deploy @nousresearch Hermes Agent with NVIDIA NemoClaw and OpenShell, connect it to Slack, Outlook, GitHub, and NVIDIA developer forums, then turn a chat correction into a reusable skill.

Private data stays behind runtime policies. Learned skills persist across deployments.

[NVIDIA AI @NVIDIAAI]

Self-Evolving Hermes Agents: Enterprise AI That Gets Better With Use | Nemotron Labs https://t.co/1ISEc9Vdy8

[Nous Research @NousResearch]

We have worked with @nvidia to integrate their official Agent Skills catalog into the Hermes Skills Hub.

These skills teach your agent how to use CUDA-X libraries, Omniverse and Physical AI workflows, NeMo training and inference tools, and other platform components.

[Olares @Olares_OS]

We are excited to share that NVIDIA NemoClaw now runs on Olares OS!

You can now run your entire AI agent stack locally and securely on devices ranging from the Olares One desktop to NVIDIA DGX Spark systems. @NVIDIA_AI_PC

Learn more:
https://t.co/FgHZTeiI1U

[Kris Murphy @KrisMMurph]

My Technovation team is going to the worldwide finals! @technovationMN
http://t.co/Jei94XtXCs

[Kris Murphy @KrisMMurph]

Check out Kasson-Mantorville Students Heading to Prestigious Event http://t.co/uARErxmYml @KROC1340

[Sharie Furst @s_furst]

Way to go, Girls! I'm so proud of Rylee, Andera, and Lydia!! https://t.co/Ota8ig1Ys5

[Kris Murphy @KrisMMurph]

CONGRATS. Furst class.. one of three regoinal champs from Minnesota @technovationmn

[Kris Murphy @KrisMMurph]

@technovationMN so proud of my #technovation team, Furst class from Kasson-Mantorville Middle school.