GenerateForgex
vertical sim2real data-factory engine producing perfectly-labeled RGB, segmentation, depth, force, and trajectory data.
Open ForgexProducts
The closed-loop product suite for robot data teams.
Generate, calibrate, evaluate, and curate synthetic robot data with a unified SimMint stack.
Warehouse AI CoNorthstar OEMVector RoboticsAtlas FulfillmentKinetic LabsAisleWorks
Products
Filter the factory loop.
Sort by name or operational phase.
GenerateCalibrateCalibra
real-to-sim site-calibration model that matches a customer environment.
Open CalibraEvaluateVeridex
transfer evaluator and failure taxonomy that gates real-world readiness.
Open VeridexCurateCurrix
agentic curriculum engine choosing scenarios that maximize policy lift per GPU-hour.
Open CurrixWorkflow
How the products reinforce each other
SimMint replaces one-off data projects with an operating loop that continuously improves robot models.
Generate
Produce perfectly labeled synthetic scenes.
Calibrate
Match sites, sensors, light, materials, and motion.
Evaluate
Score transfer and classify failures.
Curate
Choose the next scenarios for maximum policy lift.
SimMint system
What teams buy
Data-as-a-service with measurable outputs.
Recurring generation
Production labels and scenes.
Site matching
Updates after layout and SKU changes.
Transfer scoring
Evidence before rollout.
92%
average scene-match calibration score
48M
perfect labels produced per monthly factory
31%
policy lift from curriculum-led regeneration
Product gallery
Dark operational interfaces for robot data teams.
CSS-drawn panels visualize scenario inventory, drift, transfer gates, and curriculum decisions.
Technical stack
Suite-level NVIDIA foundation
Every layer is designed for GPU-scale simulation, training, and deployment evidence.
| Scene source | OpenUSD libraries |
|---|---|
| Simulation | Isaac Sim + Replicator |
| Acceleration | DGX/HGX/GB200 |
| Edge | Jetson Orin |
SimMint system
Procurement fit
Choose the start based on your bottleneck.
Forgex
vertical sim2real data-factory engine producing perfectly-labeled RGB, segmentation, depth, force, and trajectory data
Calibra
real-to-sim site-calibration model that matches a customer environment
Veridex
transfer evaluator and failure taxonomy that gates real-world readiness
Currix
agentic curriculum engine choosing scenarios that maximize policy lift per GPU-hour
FAQ
Questions teams ask before trusting synthetic robot data.
We calibrate scenes from real site evidence, evaluate transfer, and regenerate missing scenarios until models clear gates.
No. Real data anchors calibration and evaluation; synthetic data expands coverage, labels, and edge cases.
We start with warehouse perception and manipulation, then adapt to sensors, end-effectors, SKUs, and policies.
Deploy with evidence
Turn your next robot rollout into a measured sim2real program.
Bring one site, one workflow, and one target model. SimMint returns a calibrated data-factory plan.