Noether Framework
Industry-grade deep learning framework for Engineering AI.
Get started in minutes with established transformer architectures.
Train. Evaluate. Apply.












Overview
The Noether Framework is an open software framework for Engineering AI, introducing repeatable, extensible, and production-oriented workflows. Built on transformer building blocks, it delivers the full engineering stack, allowing teams to build, train, and apply industrial models across engineering verticals, eliminating the need for component re-engineering and an in-house deep learning team.

Streamlined Data Management
We enable efficient and scalable data handling for AI-driven physics applications. Datasets access via storage provider of choice: HuggingFace, AWS S3, etc.
Optimized data pipeline that support high dimensionality data serving for training. Buildings blocks for flexible data preprocessing.

Scalable AI Training
A fully configurable training pipeline built for Large Engineering Models. Supports distributed GPU clusters, mixed precision, and dynamic scheduling with intuitive, easy-to-read YAML configs. From CFD meshes to volumetric data, training is both reproducible and performance-tuned with our ready to use model architectures.

Inference
Optimized inference ensures high performance and scalability of trained models. Emmi AI also offers a growing library of ready-to-use, pre-trained physics models, allowing users to accelerate simulation tasks and integrate intelligent solutions out of the box.
Flexible
Noether Framework can be used with different hardware. We illustrate time scaling required to train AB-UPT model over ShapeNet-Car dataset for 10 epochs. Benchmarks conducted with batch size 1 per GPU and at FP32 precision.
Ready for Production?
Noether framework is open-source and ready to use. For commercial deployments, enterprise support, custom model development, or integration assistance, our team is here to help accelerate your Engineering AI initiatives.

Let's Build Together
Discuss your use case with our team and explore how Emmi AI can transform your simulation workflows.

