# rosejn/cortex

Machine learning in Clojure

Repository: https://github.com/rosejn/cortex
Canonical: https://ross.abutalabs.com/products/rosejn-cortex
Language: Clojure
License: EPL-1.0
License Family: copyleft
Last push: 2018-09-10T20:29:23+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3627, "days_push": 2914, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1271, forks 108 (observed 2026-08-28T04:04:11.924412+00:00)

## What it is
Cortex is a Clojure machine learning library providing neural networks, regression, and feature learning on the JVM, with optional GPU acceleration through CUDA and cuDNN. It was developed by ThinkTopic and is distributed via Clojars, with examples such as MNIST classification for training classifiers and regressors.

## Use cases
- train neural networks in clojure
- deep learning on the jvm
- build classifiers and regressions from clojure
- gpu accelerated machine learning from clojure
- mnist classification example in clojure
- feature learning in clojure

## When to choose
- you are working in Clojure and want ML without leaving the JVM
- you want to train simple classifiers or regressions with EDN/nippy-serializable models
- you want CUDA/cuDNN-backed GPU training from Clojure code

## When to avoid
- you need a stable, production-grade deep learning framework with a fixed model save format
- you need recurrent networks, multi-GPU, or large pre-trained models like VGG
- you need an actively maintained project with recent releases

## Facets
- artifact type: library
- maturity: abandoned
- function: machine-learning, deep-learning, gpu-computing
- domain: machine-learning, deep-learning, data-science
- platform: jvm
- tags: clojure, neural-networks, regression, feature-learning, cuda, cudnn, mnist, jvm, nippy-serialization, gpu

## Member repositories
- rosejn/cortex (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:11.924412+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 2026-08-30T05:03:23.874089+00:00, confidence not recorded.
  - readme: https://github.com/rosejn/cortex (fetched 2026-08-28T04:04:11.924412+00:00, sha 967c4541dd7c)
- Data as of 2026-08-30T08:39:29.467469+00:00.