Cross-machine perception
Board caliper and moisture, print registration and color, die and anvil wear, glue temperature, fold squareness and stacking, sensed together, not in silos.
Products
Six agents. One plant. One flywheel.
Each product maps one-to-one onto the physical converting flow: board making, printing, die-cutting, folding and gluing, and end-of-line, all orchestrated by a physics-informed digital twin.
Land on any machine, expand to the whole plant
Every product shares the same plant-edge data flywheel, cross-vendor connectors and serving fabric, so the ecosystem compounds.
Board making
Corvex
Autonomous corrugator and board-bond control
Runs the corrugator to hold warp-free, on-strength board across grades and humidity.
Explore Corvex PrintingChromata
Autonomous registration, brand-color and print-defect control
Keeps every impression on-register and on-brand across flexo, litho and digital.
Explore Chromata Die-cut and creaseKreasa
Autonomous die-cut, crease and nesting yield
Maximises board yield and holds clean cuts and sound creases.
Explore Kreasa Fold and glueGluvex
Autonomous folder-gluer fold-and-glue control
Eliminates skips, fishtails and misfolds for square, sound boxes.
Explore Gluvex End-of-linePalvex
Physical-AI robotic feeding, stacking and palletizing
Drives robotic feeding, stacking, bundling and palletizing at line speed.
Explore Palvex Twin and OEETwinflo
Converting-line-and-box twin with waste, energy and OEE
Simulates the line to hit quality and yield before the run, and orchestrates the agents.
Explore TwinfloHow the six compose
| Product | Stage | What it does | Primary NVIDIA hardware |
|---|---|---|---|
| Corvex | Board making | Autonomous corrugator and board-bond control | Jetson Orin and Thor, DGX, Omniverse |
| Chromata | Printing | Autonomous registration, brand-color and print-defect control | Jetson Orin and Thor, DGX, Cosmos |
| Kreasa | Die-cut and crease | Autonomous die-cut, crease and nesting yield | Jetson, cuOpt, Omniverse and Isaac |
| Gluvex | Fold and glue | Autonomous folder-gluer fold-and-glue control | Jetson Orin and Thor, Isaac, Cosmos |
| Palvex | End-of-line | Physical-AI robotic feeding, stacking and palletizing | Jetson, Isaac Sim and Lab, DGX |
| Twinflo | Twin and OEE | Converting-line-and-box twin with waste, energy and OEE | OVX and RTX, Omniverse and Modulus, cuOpt |
The outputs of one agent are the training signal for the next
Board strength informs fold and stacking; print and fold defects inform makeready; the twin calibrates against every run. The result is a defensible, cross-machine converting-quality-and-waste dataset.
- One plant-edge data flywheel: image, spectro, PLC and outcome telemetry
- Shared cross-vendor machine and MES connectors
- Common Jetson, Triton and NIM serving fabric
- Omniverse converting-line-and-box twin as the brain
6Products, one platform
5Converting stages covered
−31%Waste and makeready cut
−42%Claims cut
Six machines that finally talk to each other
Shared makeready twin
One twin tunes setup across corrugation, print and die and fold so the whole line reaches spec with less trial waste.
Compounding data
The more machines Foldeon runs, the better every agent gets, a moat single-machine vendors cannot match.
One integration surface
Cross-vendor connectors mean one contract, one edge fabric and one security model across your mixed fleet.
The value isn’t six tools. It’s that the corrugator, the press and the folder-gluer finally share one picture of quality, and act on it.
Bond strength
46lb/in
Color ΔE
0.9to brand
Crease integrity
99.9%
Palletize rate
1.4kper hour
Compose your plant, one agent at a time
Pick the wedge with the clearest ROI. We’ll show it running against a real job.