---
id: ultralytics
version: "8.4.120"
license: AGPL-3.0
license_treatment: agpl
maintenance: active
---

# ultralytics — Ultralytics YOLO 🚀 for SOTA object detection, multi-object tracking, instance segmentation, pose estimation, classification, and oriented object detection.

License: agpl · Maintenance: active · Downloads: 9.0M/mo

## What it is and what it does

Ultralytics YOLO is a production-grade computer vision framework built around the YOLO family of models (YOLOv3 through YOLO26). It provides a unified Python API and CLI for training, validating, and deploying models across multiple vision tasks: object detection, instance and semantic segmentation, pose estimation, image classification, and oriented object detection. The package wraps PyTorch models and includes utilities for data loading, metric computation, and model export to formats like ONNX.

The framework is designed for both research and production use, with pre-trained weights available for immediate inference and a training pipeline that accepts custom datasets via YAML configuration. It depends on torch, torchvision, opencv-python, numpy, matplotlib, and several utility libraries for GPU monitoring and platform integration. The AGPL-3.0 license means derivative works must be open-sourced; commercial deployment requires a separate license.

Use it for:

- Train a custom object detector on your own dataset and export it to ONNX for deployment in a production service.
- Use a pre-trained YOLO model to detect and track objects in video streams or live camera feeds.
- Perform pose estimation on images to extract human keypoints for fitness or motion-capture applications.
- Build an image classification pipeline that classifies thousands of images using a pre-trained model.
- Segment instances in medical or satellite imagery and export results for downstream analysis.
- Benchmark model performance across different YOLO variants to choose the best speed-accuracy tradeoff for your hardware.

## Worth the install?

AI-flagged interpretation of the facts above — verify before relying.

Ultralytics YOLO provides a unified framework for training and deploying computer vision models for object detection, instance segmentation, pose estimation, image classification, and semantic segmentation tasks.

Yes, with conditions. Ultralytics YOLO is a mature, actively maintained framework ideal for computer vision projects that need object detection, segmentation, or pose estimation. Install it if you need a production-ready YOLO implementation and can accept the AGPL-3.0 license (or obtain a commercial license). The 14 runtime dependencies are substantial—particularly torch and torchvision—so ensure your environment can accommodate them. No known security vulnerabilities as of the latest release.

## Install

pip install ultralytics
uv add ultralytics
poetry add ultralytics

## Installing ultralytics

Before you install: Low install friction with a pure-Python wheel distribution. Actively maintained with a release within the last day and 60624 repository stars. Requires PyTorch>=1.8 and Python>=3.8; the 14 runtime dependencies include torch, torchvision, opencv-python, and numpy, which are substantial but standard for computer vision work.

License in practice: Licensed under AGPL-3.0, which requires that any modifications or derivative works distributed must also be released under AGPL-3.0 and provide source code access. Commercial use requires an Enterprise License from Ultralytics.

Quickstart:

pip install ultralytics

from ultralytics import YOLO

model = YOLO('yolo26n.pt')
results = model.predict(source='image.jpg')
results[0].show()

Requires PyTorch>=1.8 and Python>=3.8; GPU acceleration (via torch and torchvision) is optional but recommended for practical inference and training workloads.

Verify before relying:

- Whether pre-trained model weights are automatically downloaded on first use or require manual setup.
- Whether the package supports inference on edge devices or requires a full PyTorch installation.
- Performance characteristics (inference speed, memory usage) on CPU-only systems versus GPU.
- Whether the AGPL-3.0 license restriction applies to closed-source applications that only call the package without modifying it.

## Package facts

- License: AGPL-3.0 (agpl)
- Python support: supports_current
- Install friction: low
- Maintenance: active
- Downloads: 9.0M/month (top 5,000 on PyPI)
- Known vulnerabilities: none known

## Tags

yolo object detection, computer vision deep learning, instance segmentation training, pose estimation models, image classification pytorch, real-time object detection, model training framework, computer-vision, object-detection, deep-learning

[View on SkillFed](https://skillfed.io/packages/ultralytics) · [View on PyPI](https://pypi.org/project/ultralytics/)