# salesforce/TransmogrifAI

TransmogrifAI (pronounced trăns-mŏgˈrə-fī) is an AutoML library for building modular, reusable, strongly typed machine learning workflows on Apache Spark with minimal hand-tuning

Repository: https://github.com/salesforce/TransmogrifAI
Canonical: https://ross.abutalabs.com/products/transmogrifai
Homepage: https://transmogrif.ai
Language: Scala
License: BSD-3-Clause
License Family: permissive
Topics: ml, automl, transformations, estimators, dsl, pipelines, machine-learning, scala, salesforce, einstein, features, feature-engineering, spark, sparkml, ai, automated-machine-learning, transmogrification, transmogrify, structured-data, transformers
Last push: 2026-06-02T18:03:07+00:00

## Health v2 (maintenance only)
Score: 61/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 85, release rhythm 8, longevity 100
- inputs: {"age_days": 3226, "days_push": 92, "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 2277, forks 399 (observed 2026-08-28T04:06:33.567019+00:00)

## What it is
TransmogrifAI is an AutoML library written in Scala that runs on Apache Spark for building modular, reusable, strongly typed machine learning workflows on structured data. It automates feature engineering, feature validation, and model selection, achieving near hand-tuned accuracy with far less effort.

## Use cases
- automate feature engineering and model selection on structured data
- build production ML pipelines on Apache Spark
- build machine learning models without deep ML expertise
- create modular reusable strongly typed ML workflows
- automated machine learning for tabular data
- reduce time to train and tune Spark ML models

## When to choose
- you already run Apache Spark and want AutoML on structured/tabular data
- you want compile-time type-safe, modular ML workflow definitions in Scala
- you need fast production-ready ML pipelines with minimal hand-tuning

## When to avoid
- you need deep learning or unstructured data like images and text
- you work in Python-only ecosystems like scikit-learn or AutoML tools
- you need a project with frequent updates and modern Spark version support

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, etl, data-science
- domain: machine-learning, big-data, data-science
- platform: jvm, python
- tags: automl, spark, feature-engineering, structured-data, type-safe, salesforce-einstein

## Member repositories
- salesforce/TransmogrifAI (main) score 61

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:33.567019+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 2026-08-30T02:41:27.030053+00:00, confidence not recorded.
  - readme: https://github.com/salesforce/TransmogrifAI (fetched 2026-08-28T04:06:33.567019+00:00, sha f65d86a8968d)
  - homepage: https://transmogrif.ai (fetched 2026-08-29T10:22:01.556173+00:00, sha 00656003e182)
- Data as of 2026-08-30T08:39:29.467469+00:00.