Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
OpenNN - Open Neural Networks Library
| Date | Stars |
|---|---|
| 2026-08-05 | 1197 |
| 2026-08-06 | 1197 |
| 2026-08-13 | 1197 |
| 2026-08-14 | 1197 |
| 2026-08-18 | 1198 |
| 2026-08-22 | 1198 |
| 2026-09-02 | 1199 |
| 2026-09-11 | 1198 |
| 2026-09-12 | 1198 |
| 2026-09-20 | 1198 |
| 2026-09-21 | 1198 |
| 2026-09-27 | 1199 |
| 2026-09-28 | 1200 |
| 2026-10-02 | 1201 |
| 2026-10-05 | 1202 |
| 2026-10-09 | 1203 |
| 2026-10-10 | 1204 |
| 2026-10-11 | 1203 |
| 2026-10-13 | 1203 |
| 2026-10-14 | 1203 |
| 2026-10-19 | 1203 |
| 2026-10-29 | 1203 |
| 2026-10-30 | 1204 |
| 2026-10-31 | 1204 |
| 2026-11-04 | 1204 |
Today
— stars today
This week
+1 stars this week
This month
+2 stars this month
Momentum
36.0
growth rate 0.08%/day
# OpenNN OpenNN is a C++20 library for building, training and running neural networks. It supports tabular data, images, time series and text, with CPU and optional CUDA execution. Models can be embedded in C++ applications or exported as standalone source code for supported architectures. | I want to… | Start here | | --- | --- | | Build and run my first network | [Quick start](#quick-start) | | Choose CPU/CUDA backends and build options | [Build options](AGENTS.md#build-options) | | Use OpenNN in my C++ application | [Install and link](#use-opennn-in-your-application) | | Train, evaluate or export a model | [Examples](examples/README.md) | | Update an 8.x application or model | [Migration](AGENTS.md#migrating-from-8x-to-260) | | Understand the source folders | [Repository contents](#repository-contents) | | Run or review performance comparisons | [Benchmarks](benchmarks/README.md) | | Contribute or run the tests | [Contributing](#contributing-and-support) | | Use OpenNN under the AGPL or a commercial licence | [License](#license) | Tutorials are available on [opennn.net](https://www.opennn.net/). ## Quick start You need Git, CMake 3.24+, and a C++20 compiler with `std::format` and OpenMP: GCC 13+, Clang 17+, or Visual Studio 2022 C++ tools. On macOS, install the OpenMP runtime (`libomp`). CMake retrieves missing dependencies during the first configuration, so that step needs internet access. Clone the repository and configure a CPU build: ```sh git clone https://github.com/Artelnics/opennn.git cd opennn cmake -S . -B ../opennn-build -DCMAKE_BUILD_TYPE=Release -DOpenNN_DISABLE_CUDA=ON -DOpenNN_BUILD_TESTS=OFF -DOpenNN_BUILD_EXAMPLES=ON cmake --build ../opennn-build --config Release --target blank --parallel ``` Run the blank example on Linux/macOS or with a single-configuration generator: ```sh ../opennn-build/bin/blank ``` With Visual Studio on Windows: ```powershell ../opennn-build/bin/Release/blank.exe ``` Next, follow the [Iris example](examples/README.md#train-your-first-model) to train a classifier, evaluate it and export predictions as C or Python code. ### CUDA builds Install a C++20-compatible CUDA toolkit and cuDNN 9+. Use a separate build directory so the CPU and CUDA configurations do not overwrite each other: ```sh cmake -S . -B ../opennn-build/cuda -DCMAKE_BUILD_TYPE=Release -DOpenNN_REQUIRE_CUDA=ON -DOpenNN_BUILD_TESTS=OFF -DOpenNN_BUILD_EXAMPLES=OFF cmake --build ../opennn-build/cuda --config Release --target opennn --parallel ``` Require CUDA explicitly to make missing GPU build dependencies an error. See [CUDA batch preparation](AGENTS.md#cuda-batch-preparation) to configure workers and host/device buffers independently. ## Use OpenNN in your application Install a completed build to a separate prefix: ```sh cmake --install ../opennn-build --config Release --prefix ../opennn-install ``` In your application's `CMakeLists.txt`, consume the installed target: ```cmake cmake_minimum_required(VERSION 3.24) project(MyApplication LANGUAGES CXX) find_package(OpenNN 26.0 CONFIG REQUIRED) add_executable(my_application main.cpp) target_link_libraries(my_application PRIVATE OpenNN::opennn) target_compile_features(my_application PRIVATE cxx_std_20) ``` Configure the application with `-DCMAKE_PREFIX_PATH=/absolute/path/to/opennn-install`. The exported target supplies OpenNN's include paths and dependency linkage, and the package still works after moving the install prefix. [The package consumer](tools/package_smoke/) is a complete working example. Fetched Eigen and zlib are installed with the library. OpenMP, oneTBB, oneDNN, MKL and NVIDIA runtimes are not copied into the installation; supply those selected by the build. The installed package locates oneDNN and macOS libomp on the consuming machine; use `CMAKE_PREFIX_PATH`, `OpenNN_ONEDNN_ROOT`, or `LIBOMP_INCLUDE_DIR` and `LIBOMP_LIBRARY` for nonstandard installations. Use a compiler compatible with the one that built the package. Installation packag
Excerpt of 6,591 characters
Read on GitHub
2.4k
1.1k
678
660
523
516
428
411
246
201
194
160
158
144
114
109
109
73
60
46
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:2cd5e7d9ce55ef33, llm:repo name and description: 'OpenNN - Open Neural Networks Library' (C++)
matched fp:2cd5e7d9ce55ef33, llm:repo name and description: 'OpenNN - Open Neural Networks Library' (C++)
matched fp:2cd5e7d9ce55ef33, llm:repo name and description: 'OpenNN - Open Neural Networks Library' (C++)