Overview
Training and inference tools for object detection, segmentation and pose estimation models. The repository is maintained under ultralytics on GitHub. Its primary language is Python. See the [project README](https://github.com/ultralytics/ultralytics#readme) for the supported workflows.
Key features
- Training and inference tools for object detection, segmentation and pose estimation models.
Requirements, installation and quick start
Use the repository installation guide to select the runtime and any required model weights. Verify operating-system and GPU compatibility before starting.
[Read the upstream installation and quickstart instructions](https://github.com/ultralytics/ultralytics#readme).
[Read the upstream installation and quickstart instructions](https://github.com/ultralytics/ultralytics#readme).
Usage
Try the documented image or video example with your own test material, inspect the results, then integrate the relevant API or processing workflow.
[Usage examples and configuration reference](https://github.com/ultralytics/ultralytics#readme).
[Usage examples and configuration reference](https://github.com/ultralytics/ultralytics#readme).
Model compatibility and use cases
Model compatibility is not stated in the repository metadata.
License and risk notes
GitHub reports AGPL-3.0 for this repository. Review the upstream license file; model weights, datasets and dependencies may have separate terms.
Source review 2026-09-05: GitHub search metadata and repository README. No runtime benchmark performed. License metadata: AGPL-3.0.
Release and maintenance
[View upstream releases](https://github.com/ultralytics/ultralytics/releases).