# harthur/brain

Simple feed-forward neural network in JavaScript

Repository: https://github.com/harthur/brain
Canonical: https://ross.abutalabs.com/products/brain
Language: JavaScript
License: MIT
License Family: permissive
Archived: true
Last push: 2020-09-03T20:20:29+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 5959, "days_push": 2190, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 7988, forks 844 (observed 2026-08-28T04:10:10.586018+00:00)

## What it is
A simple feed-forward neural network library written in JavaScript, usable in Node.js and the browser. It supports training on input/output patterns and running predictions, and is officially end-of-life in favor of brain.js and convnetjs.

## Use cases
- train a simple feedforward neural network in javascript
- approximate functions like xor with a neural net
- classify inputs like color contrast in the browser
- run a pretrained network with toJSON or toFunction
- learn how neural networks work in javascript

## When to choose
- you need a tiny, dependency-free neural network for simple patterns
- you are maintaining legacy code that already uses brain
- you want a minimal educational example of neural network training

## When to avoid
- you need an actively maintained library - use brain.js or convnetjs instead
- you need deep learning features like convolutions, recurrent networks, or GPU acceleration
- you need production-grade performance or modern tooling

## Facets
- artifact type: library
- maturity: abandoned
- function: machine-learning, deep-learning
- domain: machine-learning, artificial-intelligence, developer-tools
- platform: browser
- tags: neural-network, feedforward, javascript, deprecated, superseded-by-brainjs, nodejs

## Member repositories
- harthur/brain (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:10.586018+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 2026-08-29T17:32:34.306669+00:00, confidence not recorded.
  - readme: https://github.com/harthur/brain (fetched 2026-08-28T04:10:10.586018+00:00, sha e3b7bd7bd8fc)
- Data as of 2026-08-30T08:39:29.467469+00:00.