ultralytics
Ready-to-run object detection and segmentation models you can train on your own images in an afternoon.
Worth a timeboxed spike before you bet on it.
Teams with a physical-world counting or inspection problem: shelves, parts, vehicles, safety compliance.
A bespoke computer-vision contract, or a person watching a camera feed.
AGPL-3.0. If you ship this inside a commercial product without opening your source, you need their paid licence. Price that before you build on it.
Label two hundred of your own images and train a model. Then get the licence question answered before you write any more code.
AGPL-3.0. If you run a modified version as part of a service you offer to others, you may be required to publish your source. Many companies buy a commercial licence instead.
This is a reading of the licence label, not legal advice.
The numbers
Maintainers describe it as: “Ultralytics YOLO26, YOLO11, YOLOv8 — object detection, instance segmentation, semantic segmentation, image classification, pose estimation, object tracking”
ultralytics, in short
- Should a small team use ultralytics?
- Pilot it. Worth a timeboxed spike before you bet on it. Teams with a physical-world counting or inspection problem: shelves, parts, vehicles, safety compliance.
- What does ultralytics actually do?
- Ready-to-run object detection and segmentation models you can train on your own images in an afternoon.
- What does ultralytics replace?
- A bespoke computer-vision contract, or a person watching a camera feed.
- What is the downside of ultralytics?
- AGPL-3.0. If you ship this inside a commercial product without opening your source, you need their paid licence. Price that before you build on it.
- Can ultralytics be used in a commercial product?
- Its licence is AGPL-3.0, which carries obligations or restrictions for commercial use. Read the LICENSE file, and get a lawyer's read before you ship it inside a product you sell.
Weighed against
The connective tissue around vision models: drawing boxes, counting objects, tracking across frames, zone logic.
Screen recording and AI agent integration tool
Cross-platform ML framework for media processing
The standard library for image and video processing — cropping, detection, tracking, camera work.