Robots, autonomous vehicles, industrial vision, drone fleets — they all hit the same wall: on-site compute can't keep up with the models. Nectar closes the gap — shared GPUs on your floor, delivered and managed as a service.
Brain
nectar-box.local
Box
Box
Backed by & building with
A new generation of models gives every machine one brain — it sees and acts, coordinates the fleet, and learns from the work.
Unless on-site AI compute is your core business, doing it yourself pulls capital, people, and on-call away from the robots you're actually building.
Who runs the compute where Physical AI works?Capex shock. GPU depreciation and a resale cliff — capital tied up in hardware, not your product.
Wrong team, wrong work. Your engineers run infrastructure instead of building robots.
A 24/7 NOC you have to staff. Alert fatigue and MTTR you own forever.
A month to add a GPU. More capacity today means procurement, shipping, integration — while the fleet waits. A Box adds it inside a business day, from reserved headroom. Proven in the pilot.
It shouldn't be your job. So we make it ours — one managed compute layer.
The immersion-cooled enclosure and the GPUs inside it — capacity that serves your fleet's inference, milliseconds away.
The on-box loop that keeps the Box dependable — fuses GPU, power & cooling, and workload signals — one reliability loop over your whole stack — autoscales within reserved headroom, holds tail latency in band.
Join your control plane as a GPU worker, or let the Box bootstrap its own K3s. Same flow everywhere — designed for minutes, not days. The Spark week proves it on your cluster.
GKE
EKS
AKS
OKE
OpenShiftCoreWeave
Rancherbare-metal
Pre-configured on arrival and operated as a managed service — for years, not just the install.
Your workload data — payloads, prompts, logs — never leaves your network.
Either way, your workload data never crosses the boundary — only operational telemetry out, managed updates in.
A low-risk on-ramp: prove the fit on a small unit, then prove the KPIs on a production Box — you only step up once the last step earned it. Live in days, not quarters.
NVIDIA DGX Spark · GB10
You commit a K8s join and a week. You get proof Nectar fits your stack — integration and trust, not performance claims.
Then you decide. Non-binding either way.
Immersion-cooled · H200/B200-class
You commit a 60–90 day pilot — opex, no capex. You get the operating KPIs proven at your real scale.
What the pilot proves
Then it's just managed compute on your floor — capacity you never operate.
Start your trialTight control loops run 30–200 Hz — a 5–33 ms budget. Practical cloud round-trips measure 50–150 ms: outside the loop, before egress cost. The Box keeps inference and data on-site.
Neither. The Box serves the inference your stack calls; your agent control and orchestration stay yours, with a safe fallback if the Box is unavailable.
Two paths. K8s Join — the Box joins your existing control plane as a worker node via kubeadm or k3s-agent — a join designed for minutes, not days; the one-week Spark trial proves it on your cluster before anything scales. Standalone — it runs alongside your stack with no cluster join. Either way, your workloads aren't re-platformed and your CI/CD runs as it stands.
You choose Brain's access, too: a scoped-RBAC joined-cluster mode, or a read-only shadow mode with no cluster access at all.
Each Box runs high-VRAM, H200/B200-class GPUs — up to 24 per Box — provisioned with reserved headroom so you can scale utilization instantly. We describe the tier, not exact SKUs.
No. Your workload data never leaves your LAN. What crosses the boundary is operational, both ways: health and performance telemetry plus Brain's own aggregate-derived model and policy updates go out to Nectar; managed software and policy updates and remote remediation come in from the NOC.
A two-step on-ramp. First, a one-week POC on a Brain-managed NVIDIA DGX Spark — it proves Nectar joins your stack cleanly and that its telemetry reconciles with your ground truth. Then a production Box pilot that proves the operating KPIs at site scale over 60–90 days. No upfront capex — you pay opex.
Yes. Once you're in production, two levers: each Box ships with reserved GPU headroom, so you scale utilization up in hours, not procurement cycles — and as the fleet grows, additional Boxes add capacity. Elastic time-to-capacity is the point.
About a week on a pre-installed NVIDIA DGX Spark. The week proves integration — that Nectar slots into your stack and that its telemetry reconciles with your ground truth. Not the operating KPIs; those come with the Box pilot.
We'll reach out within one business day to schedule your Spark unit and walk through the K8s join. Nothing changes on your floor until you say so — and your workload data never leaves your network.