# tensorflow/haskell

Haskell bindings for TensorFlow

Repository: https://github.com/tensorflow/haskell
Canonical: https://ross.abutalabs.com/products/haskell
Homepage: https://tensorflow.github.io/haskell/haddock/
Language: Haskell
License: Apache-2.0
License Family: permissive
Archived: true
Last push: 2024-08-15T15:09:36+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3608, "days_push": 748, "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 1604, forks 195 (observed 2026-08-28T04:05:10.300690+00:00)

## What it is
Haskell bindings to the TensorFlow machine learning library, providing a typed API for building and training neural network models. It includes packages for core operations, gradient descent optimization, and example models like MNIST classification.

## Use cases
- build and train neural networks from Haskell
- run linear regression with gradient descent in Haskell
- classify MNIST digits using a Haskell-defined model
- define TensorFlow computation graphs with type safety
- train models on GPU from Haskell code

## When to choose
- you are a Haskell developer who wants to use TensorFlow without leaving the language
- you want type-safe construction of TensorFlow graphs
- you need to embed ML training in an existing Haskell codebase

## When to avoid
- you primarily work in Python where TensorFlow support is first-class
- you need the latest TensorFlow features or modern TF2/Keras APIs
- you want a large community and frequent updates

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, sdk
- domain: machine-learning, deep-learning, developer-tools
- platform: -
- tags: haskell-bindings, tensorflow, neural-networks, stack, gpu, linux, docker, haskell

## Member repositories
- tensorflow/haskell (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:10.300690+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 2026-08-30T03:52:21.673463+00:00, confidence not recorded.
  - readme: https://github.com/tensorflow/haskell (fetched 2026-08-28T04:05:10.300690+00:00, sha a2e40f710feb)
  - homepage: https://tensorflow.github.io/haskell/haddock/ (fetched 2026-08-29T11:23:58.875950+00:00, sha 73a30a8cd8ff)
- Data as of 2026-08-30T08:39:29.467469+00:00.