# Swift-AI/Swift-AI

The Swift machine learning library.

Repository: https://github.com/Swift-AI/Swift-AI
Canonical: https://ross.abutalabs.com/products/swift-ai
Language: Swift
License: MIT
License Family: permissive
Topics: swift, machine-learning, deep-learning, artificial-intelligence, ios, macos, ocr
Last push: 2017-05-03T22:01:09+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 3940, "days_push": 3409, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 6038, forks 552 (observed 2026-08-28T04:09:34.507373+00:00)

## What it is
Swift AI is a high-performance deep learning library written entirely in Swift, offering a flexible fully-connected neural network optimized for Apple hardware. It supports iOS and macOS via Apple's Accelerate framework, with example projects for handwriting and digit recognition.

## Use cases
- train a neural network in Swift on macOS
- recognize handwritten digits on iOS
- build deep learning apps for Apple platforms
- run handwriting recognition with a pre-trained model
- do machine learning natively in Swift

## When to choose
- you are building Swift apps on iOS or macOS and want a native neural network library
- you want lightweight, Apple-hardware-optimized fully-connected networks
- you need simple handwriting or digit recognition examples to learn from

## When to avoid
- you need CNNs, RNNs, or modern deep learning architectures - they are unimplemented
- you need cross-platform support beyond Apple platforms
- you need an actively maintained library - the last release was in 2017
- you are doing production ML - prefer Core ML or MLX

## Facets
- artifact type: library
- maturity: abandoned
- function: machine-learning, deep-learning, ocr, image-processing
- domain: machine-learning, deep-learning, artificial-intelligence, computer-vision
- platform: -
- tags: neural-networks, apple-platforms, accelerate-framework, handwriting-recognition, macos, ios, swift

## Member repositories
- Swift-AI/Swift-AI (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:34.507373+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 2026-08-29T17:49:07.900507+00:00, confidence not recorded.
  - readme: https://github.com/Swift-AI/Swift-AI (fetched 2026-08-28T04:09:34.507373+00:00, sha 1e444f950f68)
- Data as of 2026-08-30T08:39:29.467469+00:00.