# Artelnics/opennn

OpenNN - Open Neural Networks Library

Repository: https://github.com/Artelnics/opennn
Canonical: https://ross.abutalabs.com/products/opennn
Homepage: http://www.opennn.net
Language: C++
License: LGPL-3.0
License Family: copyleft
Last push: 2026-08-26T17:23:30+00:00

## Health v2 (maintenance only)
Score: 97/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 92, longevity 100
- inputs: {"age_days": 3946, "days_push": 7, "days_rel": 54, "gap_med": 5, "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 1198, forks 364 (observed 2026-08-28T04:03:57.742325+00:00)

## What it is
OpenNN is an open-source C++ library for building, training, and deploying neural networks for advanced analytics. It is dependency-free, optimized for execution speed and memory efficiency, and supports CPU (Eigen, MKL, oneDNN) and GPU (CUDA) backends with architectures including dense networks, LSTMs, CNNs, and transformers.

## Use cases
- train neural networks for regression and classification in C++
- forecast time series with LSTM networks
- build CNN models for image and signal data
- run transformer models like BERT and GPT-2 with GPU acceleration
- customer segmentation and churn prediction for business intelligence
- early diagnosis and microarray analysis in health care
- predictive maintenance and performance optimization in engineering

## When to choose
- you need a high-performance, dependency-free C++ neural network library
- you want CPU and GPU training/inference with CUDA, MKL, or oneDNN backends
- you are embedding machine learning into C++ engineering or analytics applications
- you need dense, recurrent, convolutional, or transformer architectures in one library

## When to avoid
- you prefer Python-first ecosystems like PyTorch or TensorFlow
- you need a GUI-driven tool rather than a code library (consider Neural Designer)
- your project requires a permissive license, since OpenNN is LGPL-3.0
- you need a large community and extensive third-party ecosystem

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, llm-inference, image-processing, math
- domain: machine-learning, deep-learning, artificial-intelligence, data-science, computer-vision
- platform: cpp, cross-platform, windows
- tags: neural-networks, c-plus-plus, high-performance, no-dependencies, cpu-gpu, transformers, lstm, cnn, eigen, cuda, gpu, linux, macos

## Member repositories
- Artelnics/opennn (main) score 97

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:57.742325+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 2026-08-30T06:21:07.750560+00:00, confidence not recorded.
  - readme: https://github.com/Artelnics/opennn (fetched 2026-08-28T04:03:57.742325+00:00, sha 1e153178b61c)
  - homepage: http://www.opennn.net (fetched 2026-08-29T12:28:21.057917+00:00, sha e06c1ee67ffc)
  - site_page: https://www.opennn.net/documentation/reference (fetched 2026-08-29T12:28:21.066787+00:00, sha 39cd09136d2b)
- Data as of 2026-08-30T08:39:29.467469+00:00.