Cross-machine perception
Board caliber 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 & gluing → end-of-line, all orchestrated by a physics-informed digital twin.
One platform, six agents
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 & board-bond control
Runs the corrugator to hold warp-free, on-strength board across grades and humidity.
Explore Corvex → PrintingChromata
Autonomous registration, brand-color & print-defect control
Keeps every impression on-register and on-brand across flexo, litho and digital.
Explore Chromata → Die-cut & creaseKreasa
Autonomous die-cut, crease & nesting yield
Maximises board yield and holds clean cuts and sound creases.
Explore Kreasa → Fold & 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 & palletizing
Drives robotic feeding, stacking, bundling and palletizing at line speed.
Explore Palvex → Twin & OEETwinflo
Converting-line-and-box twin + waste / energy / OEE
Simulates the line to hit quality and yield before the run, and orchestrates the agents.
Explore Twinflo →At a glance
How the six compose
| Product | Stage | What it does | Primary NVIDIA HW |
|---|---|---|---|
| Corvex | Board making | Autonomous corrugator & board-bond control | Jetson Orin / Thor · DGX · Omniverse |
| Chromata | Printing | Autonomous registration, brand-color & print-defect control | Jetson Orin / Thor · DGX · Cosmos |
| Kreasa | Die-cut & crease | Autonomous die-cut, crease & nesting yield | Jetson · cuOpt · Omniverse / Isaac |
| Gluvex | Fold & glue | Autonomous folder-gluer fold-and-glue control | Jetson Orin / Thor · Isaac · Cosmos |
| Palvex | End-of-line | Physical-AI robotic feeding, stacking & palletizing | Jetson · Isaac Sim / Lab · DGX |
| Twinflo | Twin & OEE | Converting-line-and-box twin + waste / energy / OEE | OVX / RTX · Omniverse / Modulus · cuOpt |
Ecosystem thesis
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 + outcome telemetry
- Shared cross-vendor machine and MES connectors
- Common Jetson / Triton / NIM serving fabric
- Omniverse converting-line-and-box twin as the brain
6Products, one platform
5Converting stages covered
−31%Waste & makeready cut
−42%Claims cut
Why one platform beats point tools
Six machines that finally talk to each other
Shared makeready twin
One twin tunes setup across corrugation, print and die/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.
46lb/in
Bond strength
0.9to brand
Color ΔE
99.9%
Crease integrity
1.4k/hr
Palletize rate
Compose your plant, one agent at a time
Pick the wedge with the clearest ROI. We’ll show it running against a real job.