# cazala/synaptic

architecture-free neural network library for node.js and the browser

Repository: https://github.com/cazala/synaptic
Canonical: https://ross.abutalabs.com/products/synaptic
Language: JavaScript
License: NOASSERTION
License Family: other
Last push: 2026-08-01T01:14:45+00:00

## Health v2 (maintenance only)
Score: 66/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 95, release rhythm 8, longevity 100
- inputs: {"age_days": 4355, "days_push": 33, "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 6912, forks 651 (observed 2026-08-28T04:09:51.327728+00:00)

## What it is
Synaptic is an architecture-free neural network library for JavaScript that runs in both Node.js and the browser. It supports building and training arbitrary first- and second-order neural network architectures, with built-in architectures like multilayer perceptrons, LSTM, liquid state machines, and Hopfield networks.

## Use cases
- build and train neural networks in JavaScript
- create LSTM networks in the browser
- train a perceptron to solve XOR
- experiment with different neural network architectures
- learn neural networks with JavaScript examples
- implement recurrent neural networks in Node.js

## When to choose
- you need neural networks running in the browser or Node.js with no native dependencies
- you want to define custom network architectures rather than fixed ones
- you are learning or teaching neural network fundamentals in JavaScript

## When to avoid
- you need GPU acceleration or high-performance training on large datasets
- you need modern deep learning features like convolutions, transformers, or automatic differentiation
- you require an actively developed library with recent updates and strong community support

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning
- domain: machine-learning, deep-learning
- platform: browser
- tags: neural-networks, lstm, perceptron, hopfield-network, recurrent-neural-networks, browser-compatible, javascript, nodejs

## Member repositories
- cazala/synaptic (main) score 66

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:51.327728+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 2026-08-29T17:41:28.123134+00:00, confidence not recorded.
  - readme: https://github.com/cazala/synaptic (fetched 2026-08-28T04:09:51.327728+00:00, sha 5476160d66e8)
  - registry_npm: https://registry.npmjs.org/synaptic (fetched 2026-08-29T08:37:34.379934+00:00, sha f5f52e591817)
- Data as of 2026-08-30T08:39:29.467469+00:00.