ultralytics
by ultralytics
Ultralytics is a Python package and command-line tool for running and training YOLO computer vision models. It finds and tracks objects in images and video, and can also classify images, estimate poses and segment scenes.
- Stars
- 63k
- Licence
- AGPL-3.0
- Runs on
- Your computer
- Setup
- Moderate
- Language
- Python
- Age
- 1510 days
What you can do with it
- Detect and count objects such as people, vehicles or products in photos and video
- Train a model on your own labelled images to spot items specific to your business
- Export trained models to formats such as ONNX for use in apps and devices
Make money with it
A freelancer could train custom detection models on a client's images and sell them as a set-up and maintenance service.
An idea, not financial advice. Check the licence before charging for anything built on it.
Ways a business could use it
- Build stock counting, footfall counting or quality-check tools without paying for a commercial vision service
- Offer custom camera-based monitoring, such as car park or site safety checks, to local clients
Can you use it commercially?
Free to use. Anything you distribute that includes it must be open-sourced under the same licence. Running it as an online service also counts, so a hosted version must offer its source.
Not legal advice. Read the project's licence file before building a product on it.
Getting it running
Install with "pip install ultralytics" in a Python environment with PyTorch, or use Conda or Docker.
Follow the official instructions in the project README.
Things to check
- AGPL-3.0 licence: using it in a commercial product generally means opening your source code or buying an Enterprise Licence
- Training on a CPU is slow, so a GPU is practical for custom models
- YOLO27 is mentioned as coming soon and is not yet available
Who's talking about it
- datnguyenquy94 (news-radar): AI Open Source Trends 2026-10-30 (Issue #926) Featured in a roundup
Checked 30 Oct 2026. Summary drafted by AI from the project's README.
