Ultralytics
Ultralytics YOLO26, YOLO11, YOLOv8 — object detection, instance segmentation, semantic segmentation, image classification, pose estimation, object tracking
Our verdict
A well-maintained, widely adopted project. This assessment is derived from GitHub's own repository metrics on 2026-08-24, not from hands-on testing.
Ultralytics YOLO26, YOLO11, YOLOv8 — object detection, instance segmentation, semantic segmentation, image classification, pose estimation, object tracking. The project is written primarily in Python, released under AGPL-3.0, and has 60,922 stars and 11,625 forks on GitHub. 436 contributors have committed to it, and the most recent push was 2026-08-24. The latest tagged release is v8.4.127 (2026-08-23). Figures come from the GitHub API on 2026-08-24 and are refreshed daily; the score below weighs adoption, maintenance, release discipline, contributor breadth, licence clarity and issue hygiene.
Repository
- Licence
- AGPL-3.0
- Language
- Python
- Last push
- 2026-08-24
Releases
-
v8.4.127v8.4.127 – Load exported YOLO models with the correct task across all 20 formats (#25886) -
v8.4.126v8.4.126 – Make restricted checkpoint loading thread-safe and 40% faster, simplify RLE prior (#25885) -
v8.4.125v8.4.125 – Speed up initial model loading (#25883) -
v8.4.124v8.4.124 – Restore dynamic image sizes for NMS exports (#25874) -
v8.4.123v8.4.123 – Accept existing depth dataset formats (#25859) -
v8.4.122v8.4.122 – Use canonical PNG depth maps (#25858)
Pros and cons
Pros
Cons
User reviews
No user reviews yet.
Be the first to review UltralyticsUltralytics alternatives
Side by side
| Tool | Our score | From | Free tier | Best for | |
|---|---|---|---|---|---|
| Ultralytics this page | 9.1 | — | Yes | ||
| Transformers | 9.4 | — | Yes | ||
| Tesseract | 8.9 | — | Yes | ||
| vLLM | 8.9 | — | Yes | ||
| PaddleOCR | 8.7 | — | Yes | ||
| LlamaFactory | 8.6 | — | Yes | ||
| PyTorch | 8.1 | — | Yes |