# Geekgineer/YOLOs-CPP

Cross-Platform Production-ready C++ inference engine for YOLO models (v5-v12, YOLO26). Unified API for detection, segmentation, pose estimation, OBB, and classification. Built on ONNX Runtime and OpenCV. Optimized for CPU/GPU with quantization support.

Repository: https://github.com/Geekgineer/YOLOs-CPP
Canonical: https://ross.abutalabs.com/products/yolos-cpp
Homepage: https://geekgineer.github.io/YOLOs-CPP/
Language: C++
License: AGPL-3.0
License Family: copyleft
Last push: 2026-08-23T17:16:18+00:00

## Health v2 (maintenance only)
Score: 88/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 96, longevity 49
- inputs: {"age_days": 693, "days_push": 10, "days_rel": 31, "gap_med": 2, "n_releases_24m": 4}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1076, forks 163 (observed 2026-08-28T04:03:29.390676+00:00)

## What it is
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
- artifact type: library
- maturity: active
- function: machine-learning, computer-vision, image-processing, llm-inference, sdk
- domain: computer-vision, machine-learning, deep-learning, image-processing, cross-platform, developer-tools
- platform: cpp, windows, cross-platform
- tags: yolo, onnx-runtime, opencv, object-detection, instance-segmentation, pose-estimation, obb, classification, depth-estimation, quantization, inference-engine, tensorrt, linux, macos, gpu

## Member repositories
- Geekgineer/YOLOs-CPP (main) score 88

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:29.390676+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:53:19.086173+00:00, confidence not recorded.
  - readme: https://github.com/Geekgineer/YOLOs-CPP (fetched 2026-08-28T04:03:29.390676+00:00, sha 8ee69df22b27)
  - homepage: https://geekgineer.github.io/YOLOs-CPP/ (fetched 2026-08-29T12:54:34.086951+00:00, sha 0b7206a62d12)
- Data as of 2026-08-30T08:39:29.467469+00:00.