libfann/fann

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1750 stars · 398 forks observed · 2026-08-28

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

Fast Artificial Neural Network (FANN) is a free open-source C library implementing multilayer neural networks with fully and sparsely connected topologies. It supports backpropagation and cascade2 training in fixed and floating point, with bindings to 15+ languages and cross-platform builds.

Use cases

• train a small feedforward neural network in C
• run neural network inference on embedded or fixed-point hardware
• experiment with RPROP or Quickprop training algorithms
• embed a lightweight ANN in a desktop application
• save and load trained neural network models to disk
• learn neural network fundamentals with a simple C API

When to choose

• you need a fast, lightweight C library for classic feedforward networks
• you need fixed-point arithmetic for embedded or low-resource targets
• you want a simple API with minimal dependencies and LGPL licensing
• you need bindings for many languages from one core library

When to avoid

• you need modern deep learning features like CNNs, RNNs, or GPU acceleration
• you want an actively developed ecosystem with community support
• you need automatic differentiation or autograd-style tooling
• your project is Python-first and you prefer PyTorch or TensorFlow

Facets

library · maturity maintenance

machine-learning deep-learning machine-learning artificial-intelligence cross-platform windows cross-platform cpp c neural-networks backpropagation fixed-point language-bindings c-library linux macos

Member repositories

For agents

markdown · JSON · MCP: product_card(name="libfann/fann")