Nvidia's Nader Khalil — Director of Developer Technologies and co-founder of Brev.dev, acquired by Nvidia two years ago — sat down with The New Stack to talk agents, OpenClaw, and where enterprise AI is heading.
His opening line is worth keeping:
"An agent is an LLM and a harness. And if you think about that, it involves two things. It involves the loop and the LLM… Each loop should take us closer to our goal."
That's not a complicated definition. It's also exactly right — and the fact that Nvidia's internal framing lands here matters more than the quote itself.
What actually happened
- Nvidia has full-time OpenClaw contributors. Khalil: "We have a couple of developers at the company that contribute to OpenClaw full time." That's a real commitment, not a press-release mention.
- NemoClaw is their enterprise blueprint — a reference architecture for running OpenClaw (and Hermes) in production, with GPU routing, security policies, and a runtime called OpenShell.
- Khalil traces the harness evolution directly: from ChatGPT's system prompts → memory → file context → Cursor → Claude Code. All of it is harness, not model. The model is constant; the harness is where the product lives.
- On OpenClaw's PR backlog: "It got more stars than Linux in months… so I think you're gonna see a mountain of PRs." Their response — roll up their sleeves and start merging.
Why this framing matters
Nvidia makes money when AI compute scales. For that to happen, agents need to work reliably in enterprise environments — and the harness is the reliability layer.
Their NemoClaw blueprints aren't a product play; they're an enablement play. Enterprise teams get a reference architecture that works on Nvidia silicon. Nvidia gets demand for the GPUs underneath. It's the CUDA X model applied to agentic AI.
The microwave analogy Khalil uses is useful: "when it's your microwave at home, you just go 'Boop, boop. Done.'" Every enterprise will build specialized agents tuned to their domain — CrowdStrike, Cadence, Palantir are already doing it. Nvidia wants to be the chip and the blueprint under all of them.
What to do
- Following OpenClaw? Full-time Nvidia contributions mean the PR backlog may actually start moving. Worth watching.
- Building enterprise agents? Look at NemoClaw — it's Nvidia's reference for wiring harnesses to local GPUs with policies and security built in.
- Evaluating agent frameworks? Use the "LLM + harness" lens. It's clean. Audit what's model-specific vs what lives in your tooling layer — they fail differently and you need to know which is which.
Source: The New Stack — "An agent is an LLM and a harness": What Nvidia really thinks about OpenClaw
✏️ Drafted with KewBot (AI), edited and approved by Drew.
Top comments (1)
"LLM plus harness" is a clean framing because it puts responsibility back on the loop. The model matters, but the harness decides what the agent can see, what it can touch, how it recovers, and what counts as done.