Geekgineer/YOLOs-CPP

Health v2 · maintenance only

Adoption not part of the score

1076 stars · 163 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

YOLOs-CPP is a production-ready, cross-platform C++ inference library for the YOLO model family (v5 through YOLO26), built on ONNX Runtime and OpenCV. It provides a unified API covering detection, segmentation, pose estimation, oriented bounding boxes, classification, open-vocabulary detection, and depth estimation, with CPU/GPU optimization and quantization support.

Use cases

• run yolo object detection in c++
• deploy yolo models with onnx runtime natively
• perform instance segmentation and pose estimation in c++
• run yolo inference on cpu and gpu without python
• batch process images with yolo models
• estimate monocular depth with yolo26
• integrate yolo inference into a ros2 robot
• run quantized yolo models for faster inference

When to choose

• you need high-performance YOLO inference in a native C++ application
• you want a single unified API across multiple YOLO versions and tasks
• you need cross-platform support for Linux, macOS, and Windows
• you want to avoid a Python dependency in production deployments
• you need GPU acceleration or quantized models for edge devices

When to avoid

• you need training or fine-tuning of YOLO models rather than inference
• you prefer Python tooling like Ultralytics for rapid prototyping
• your project cannot comply with the AGPL-3.0 license
• you need model architectures outside the YOLO family

Facets

library · maturity active

machine-learning computer-vision image-processing llm-inference sdk computer-vision machine-learning deep-learning image-processing cross-platform developer-tools cpp windows cross-platform yolo onnx-runtime opencv object-detection instance-segmentation pose-estimation obb classification depth-estimation quantization inference-engine tensorrt linux macos gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="Geekgineer/YOLOs-CPP")