Sign in

Ultralytics

Ultralytics YOLO26, YOLO11, YOLOv8 - object detection, instance segmentation, semantic segmentation, image classification, pose estimation, object tracking

7.7 Open source60.9k
Ultralytics homepage
platform.ultralytics.com · captured 2026-09-01
How to Train YOLO Segmentation Models with Ultralytics Platform
Ultralytics YOLO26: Annotate, Train, & Deploy Custom Model with Ultralytics Platform and Live Demo
How to Run Inference with Meta's SAM2 and MobileSAM Models using Ultralytics | Step-by-Step Guide 🎉
How to Train Ultralytics YOLO26 Model on Custom Dataset using Google Colab Notebook | Step-by-Step 🚀
Making Cricket DRS System for LBW | Computer Vision - Python - Ultralytics
JTheta.ai + Ultralytics Hub Tutorial: From Dataset to YOLO Training

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. It is written in Python. It has 60,922 stars and 436 contributors, and it was pushed to within the last few weeks. It is AGPL licensed, which is the detail to check first if you plan to build something commercial on top of it. The most recent tagged release is v8.4.127, from 2026-08-23. Figures come from the GitHub API on 2026-08-26 and refresh daily.

Reviewed by AI Review Rating from GitHub API data How we score

RepositoryGitHub API, refreshed daily

60.9kStars
11.6kForks
264Watching
436Contributors
118Open issues
Licence
AGPL-3.0
Language
Python
Last push
2026-08-24
View on GitHub

Releases

  1. v8.4.127 v8.4.127 - Load exported YOLO models with the correct task across all 20 formats (#25886)
  2. v8.4.126 v8.4.126 - Make restricted checkpoint loading thread-safe and 40% faster, simplify RLE prior (#25885)
  3. v8.4.125 v8.4.125 - Speed up initial model loading (#25883)
  4. v8.4.124 v8.4.124 - Restore dynamic image sizes for NMS exports (#25874)
  5. v8.4.123 v8.4.123 - Accept existing depth dataset formats (#25859)
  6. v8.4.122 v8.4.122 - Use canonical PNG depth maps (#25858)

Pros and cons

Pros

Cons

Pricing

  • Free tierYes
  • LicenceAGPL-3.0
  • Self-hostYes, source is public
  • Public price listNot published

Ultralytics does not publish a web price list. For consumer apps that usually means pricing appears inside the product; for enterprise tools it means talking to sales. Why we do this

Visit platform.ultralytics.com

Changelogwhat changed, most recent first

On videoclick to play, nothing loads until you do

What users actually say

We link to discussions rather than reproducing them. Opinions belong to their authors.

User reviews

No one has reviewed Ultralytics here yet. Reviews are moderated before they appear, and our own score is editorial and separate from user ratings, though once reviews land they do lift it.

Used Ultralytics? Review it.

Sign in to rate it. One account, one review per tool, so the score means something.

Create a free account Already a member? Sign in
{{ reviewsTotal }}{{ options.labels.singularReviewCountLabel }}
{{ reviewsTotal }}{{ options.labels.pluralReviewCountLabel }}
{{ options.labels.noReviewsLabel }}
{{ options.labels.newReviewButton }}
{{ userData.canReview.message }}

Ultralytics alternatives

Side by side

ToolOur scoreFrom Free tierBest for
Ultralytics this page 7.7 - Yes
🥇Roboflow Supervision 7.7 - Yes
🥈OCRmyPDF 7.6 - Yes
🥉Tesseract 7.6 - Yes
Frigate 7.5 - Yes
PaddleOCR 7.5 - Yes
MediaPipe 7 - Yes

Questions

Is Ultralytics free?

Yes. Ultralytics advertises a free tier on its own site.

How much does Ultralytics cost?

Ultralytics does not publish pricing openly, which usually means it is quote-based. You will need to contact the vendor.

Is Ultralytics open source?

Yes. Ultralytics is a public repository released under AGPL-3.0. You can self-host or inspect the source directly.

How is Ultralytics scored here?

Ultralytics scores 7.7 out of 10. That comes from a desk review of public evidence, which is capped at 8.5 out of 10: public pricing, documentation, maintenance signals and how much we could actually verify. Affiliate relationships are excluded from scoring entirely. The full rubric is published on our methodology page.

Related