open-edge-platform/geti

Health v2 · maintenance only

Adoption not part of the score

1338 stars · 479 forks observed · 2026-09-24

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Geti is an open-source, end-to-end Vision AI application from Intel that takes users from raw images to deployed computer vision models, running locally as a single container or native Windows app. It includes the getitune training engine (formerly OpenVINO Training Extensions/otx) with 67+ state-of-the-art model architectures for object detection, segmentation, and classification, optimized for inference on Intel XPU, CPU, and NVIDIA CUDA hardware.

Use cases

• train object detection models on my own images
• build an image classification model with minimal data
• train image segmentation models locally
• optimize and quantize vision models for edge inference with OpenVINO
• run AutoML to find the best computer vision model for my dataset
• deploy a vision model for live inference on Intel GPU
• do transfer learning from pretrained YOLO or DETR models
• annotate images and manage datasets for vision training

When to choose

• you want an end-to-end local workflow from raw images to deployed vision models
• you target Intel hardware (CPU, XPU) or NVIDIA CUDA for training and inference
• you need state-of-the-art detection, segmentation, or classification architectures without writing training code
• you want OpenVINO-optimized models for edge deployment
• you prefer a self-hosted GUI application or REST API over notebooks

When to avoid

• you need tasks beyond computer vision such as NLP, audio, or LLMs
• you require cloud-scale distributed training across many nodes
• you want a lightweight Python library only - though getitune covers that, the full app is heavyweight
• you depend on non-Intel accelerators other than NVIDIA CUDA
• you need the deprecated otx package API specifically

Facets

application · maturity active

machine-learning deep-learning computer-vision image-processing llm-training computer-vision machine-learning deep-learning image-processing windows python self-hosted openvino automl object-detection image-segmentation image-classification model-optimization quantization transfer-learning edge-ai intel-xpu nvidia-cuda vision-ai docker linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="open-edge-platform/geti")