# codeplea/genann

simple neural network library in C99

Repository: https://github.com/codeplea/genann
Canonical: https://ross.abutalabs.com/products/genann
Homepage: https://codeplea.com/genann
Language: C
License: Zlib
License Family: permissive
Topics: backpropagation, genetic-algorithm, ann, neural-network, c, tiny, feedforward-neural-network, machine-learning, single-file
Last push: 2026-08-08T10:34:42+00:00

## Health v2 (maintenance only)
Score: 97/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 96, release rhythm 96, longevity 100
- inputs: {"age_days": 3858, "days_push": 25, "days_rel": 27, "gap_med": 0, "n_releases_24m": 2}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2280, forks 271 (observed 2026-08-28T04:06:33.780850+00:00)

## What it is
Genann is a minimal, well-tested C99 library for training and running feedforward artificial neural networks. It is contained in a single source file and header with no dependencies, supporting backpropagation and alternative training methods like genetic algorithms.

## Use cases
- train a small feedforward neural network in C
- embed a tiny neural network in an embedded or resource-constrained project
- train an ANN with backpropagation on labeled data
- use genetic algorithms or custom optimizers to train a network
- load and run a saved neural network from a file
- learn neural network fundamentals from a simple readable implementation

## When to choose
- you need a dependency-free, single-file neural network library in C or C++
- you want a small, fast, thread-safe ANN for embedded or low-resource environments
- you want a hackable, easy-to-extend codebase for learning or experimentation
- you need feedforward networks with backpropagation or custom training loops

## When to avoid
- you need GPUs, convolutions, recurrent networks, or modern deep learning features
- you want automatic differentiation or high-level frameworks like PyTorch or TensorFlow
- you need large-scale training on big datasets
- you prefer a language other than C

## Facets
- artifact type: library
- maturity: stable
- function: machine-learning, deep-learning
- domain: machine-learning, artificial-intelligence, developer-tools
- platform: c, cross-platform, embedded
- tags: neural-network, feedforward, backpropagation, single-file, no-dependencies, genetic-algorithms, tiny

## Member repositories
- codeplea/genann (main) score 97

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:33.780850+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 2026-08-30T02:41:22.370751+00:00, confidence not recorded.
  - readme: https://github.com/codeplea/genann (fetched 2026-08-28T04:06:33.780850+00:00, sha ee50b491c796)
  - homepage: https://codeplea.com/genann (fetched 2026-08-29T10:21:38.200750+00:00, sha fdf2b50ee7c3)
  - site_page: https://codeplea.com/about (fetched 2026-08-29T10:21:38.209998+00:00, sha 5f92223ee9f2)
- Data as of 2026-08-30T08:39:29.467469+00:00.