# wagenaartje/neataptic

:rocket: Blazing fast neuro-evolution & backpropagation for the browser and Node.js

Repository: https://github.com/wagenaartje/neataptic
Canonical: https://ross.abutalabs.com/products/neataptic
Homepage: https://wagenaartje.github.io/neataptic/
Language: JavaScript
License: NOASSERTION
License Family: other
Topics: genetic-algorithm, neural-network, mutations, crossover, squash, neurons, selection, machine-learning
Last push: 2019-08-01T12:31:18+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 3478, "days_push": 2589, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1222, forks 288 (observed 2026-08-28T04:04:02.511330+00:00)

## What it is
Neataptic is a JavaScript neural network library supporting architecture-free networks trained via neuro-evolution (NEAT) and fast backpropagation, usable in the browser and Node.js. It allows building networks neuron-by-neuron or with built-in architectures like LSTM and GRU.

## Use cases
- train a neural network to learn XOR with backpropagation
- evolve neural network topologies with a genetic algorithm
- build custom neural networks with LSTM and GRU layers in JavaScript
- run neuro-evolution in the browser for game AI agents
- remove neurons and synapses from a network dynamically

## When to choose
- you need architecture-free or evolving neural networks in JavaScript
- you want NEAT-style neuro-evolution in the browser or Node.js
- you need fast backpropagation training in a JS environment

## When to avoid
- you need a maintained library with active support and updates
- you need GPU acceleration or production-grade deep learning
- you work outside JavaScript/Node.js

## Facets
- artifact type: library
- maturity: abandoned
- function: machine-learning, deep-learning
- domain: machine-learning, artificial-intelligence
- platform: browser
- tags: neural-networks, neuroevolution, genetic-algorithm, backpropagation, neat, nodejs, javascript

## Member repositories
- wagenaartje/neataptic (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:02.511330+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 2026-08-30T06:15:39.689884+00:00, confidence not recorded.
  - readme: https://github.com/wagenaartje/neataptic (fetched 2026-08-28T04:04:02.511330+00:00, sha c44a687ad0ce)
  - homepage: https://wagenaartje.github.io/neataptic/ (fetched 2026-08-29T12:24:02.685689+00:00, sha 7eac4bbf1baf)
  - registry_npm: https://registry.npmjs.org/neataptic (fetched 2026-08-29T12:24:02.694669+00:00, sha 9df6842f86f5)
- Data as of 2026-08-30T08:39:29.467469+00:00.