ultralytics
Ultralytics YOLO 🚀 for SOTA object detection, multi-object tracking, instance segmentation, pose estimation, classification, and oriented object detection.
Decision gist · record as of 2026-08-14
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.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires PyTorch>=1.8 and Python>=3.8; GPU acceleration (via torch and torchvision) is optional but recommended for practical inference and training workloads.
- Low install friction with a pure-Python wheel distribution.
- Actively maintained with a release within the last day and 60624 repository stars.
License · maintenance · safety
AGPL-3.0 (agpl) — 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.
last release 2026-08-13 (1 days) · last repo commit 2026-08-14 · 60,624 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 8,965,875 downloads/mo, #1,571 on PyPI
Alternatives
Verify before relying
pip install ultralytics
from ultralytics import YOLO
model = YOLO('yolo26n.pt')
results = model.predict(source='image.jpg')
results[0].show()- 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.
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 on this page. Verify before relying on it.
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
ultralytics on PyPI
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.
Requires PyTorch>=1.8 and Python>=3.8; GPU acceleration (via torch and torchvision) is optional but recommended for practical inference and training workloads.
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()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 the current Python release >=3.8 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 14 packagesfilelocknumpymatplotlibopencv-pythonpillowpyyamlrequeststorchtorchvisionpsutilpolarsnvidia-ml-pyultralytics-thopultralytics-platform |
| Maintenance | Actively maintained 1 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 8,965,875 / month, #1,571 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 5 - Production/StableIntended Audience :: DevelopersIntended Audience :: EducationIntended Audience :: Science/ResearchLicense :: OSI Approved :: GNU Affero General Public License v3 or later (AGPLv3+)Operating System :: MacOSOperating System :: Microsoft :: WindowsOperating System :: POSIX :: LinuxProgramming Language :: Python :: 3Programming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13Programming Language :: Python :: 3.8Programming Language :: Python :: 3.9Topic :: Scientific/EngineeringTopic :: Scientific/Engineering :: Artificial IntelligenceTopic :: Scientific/Engineering :: Image RecognitionTopic :: Software Development |
Evidence: ultralytics-8.4.120-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “instance segmentation training”
- ultralyticsUltralytics YOLO provides a unified framework for training and…
- mmdetMMDetection is an object detection and instance segmentation…
- faster-coco-evalFaster-COCO-Eval provides a high-performance replacement for COCO…
Give your agent the search over MCP, or paste the wish link into any chat.
More Software Development packages
Provides backported and experimental type hints for Python 3.9+, allowing use of newer typing features on older Python versions and enabling early experimentation with type system PEPs before they enter the standard library.
NumPy provides an N-dimensional array object and a comprehensive suite of mathematical, linear algebra, Fourier transform, and random number functions for scientific computing in Python.
FastAPI is a Python web framework for building REST APIs using type hints, with automatic request validation, serialization, and interactive API documentation.
Provides a way to document function parameters, class attributes, return types, and variables inline using Python's `Annotated` type hint syntax instead of traditional docstrings.
Typer builds command-line applications from Python functions using type hints, automatically generating help text, argument parsing, and shell completion.
Install it if you are building CLIs in Python.
Distlib provides low-level packaging utilities for building, distributing, and managing Python software—including metadata handling, version specifiers, wheel support, script installation, and dependency resolution.
See also yolov5 · sahi · groundingdino-py · pybboxes · albumentations · pytorchcv · controlnet-aux · rf100vl · nnunetv2 · segmentation-models-pytorch