codeplea/genann

Health v2 · maintenance only

Adoption not part of the score

2280 stars · 271 forks observed · 2026-08-28

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

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

library · maturity stable

machine-learning deep-learning machine-learning artificial-intelligence developer-tools c cross-platform embedded neural-network feedforward backpropagation single-file no-dependencies genetic-algorithms tiny

Member repositories

For agents

markdown · JSON · MCP: product_card(name="codeplea/genann")