cuvis-ai 0.11.1

Collaborative Framework for Hyperspectral Intelligence

Cuvis.AI

Cuvis.AI is an opensource and extensible framework for building AI powered processing pipelines for hyperspectral video data. It allows you to process and structure spectral data, train and apply machine learning models, visualize and interpret results, and deploy applications in real time environments. Pipelines are built from reusable modular nodes and can be extended with custom plugins or external integrations. Cuvis.AI bridges the gap between hyperspectral hardware and real world applications and enables faster development, testing, and deployment of new solutions.

Platform

Cuvis.AI is split across three repositories:

Repository	Role
cuvis-ai-core	Framework — base Node class, pipeline orchestration, two-phase training, gRPC services, plugin system
cuvis-ai-schemas	Shared Protobuf / gRPC schema definitions and generated types
cuvis-ai (this repo)	Catalog — 40+ domain-specific nodes for anomaly detection, preprocessing, band selection, and more

Data I/O lives in the cuvis-ai-dataloader plugin: pluggable hyperspectral DataModules (cu3s + COCO, TIFF + paired PNG). It owns the Cuvis SDK dependency, so install it there if you need .cu3s / .cu3 reads.

Quick Start

As a library (in your own project):

uv add cuvis-ai

GPU support: For PyTorch with CUDA, see the Installation Guide for setup instructions.

For development (within this repo):

uv sync

See the Installation Guide for prerequisites and detailed setup.

Documentation

Full documentation is available at https://docs.cuvis.ai/latest/.

• Quick Start
• Core Concepts
• Node Catalog
• Plugin System
• API Reference
• Contributing

Links

• Website: https://www.cubert-hyperspectral.com/
• Support: http://support.cubert-hyperspectral.com/
• Issues: https://github.com/cubert-hyperspectral/cuvis-ai/issues
• Changelog: CHANGELOG.md

---

Apache License 2.0 — see LICENSE.