# PreferredAI/cornac

A Comparative Framework for Multimodal Recommender Systems

Repository: https://github.com/PreferredAI/cornac
Canonical: https://ross.abutalabs.com/products/cornac
Homepage: https://cornac.preferred.ai
Language: Python
License: Apache-2.0
License Family: permissive
Topics: recommender-system, recommendation-algorithms, recommendation-engine, matrix-factorization, collaborative-filtering, multimodal-learning, recommendation-system, multimodality
Last push: 2026-08-11T18:52:11+00:00

## Health v2 (maintenance only)
Score: 96/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 97, release rhythm 93, longevity 100
- inputs: {"age_days": 2969, "days_push": 22, "days_rel": 49, "gap_med": 25.5, "n_releases_24m": 9}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1053, forks 171 (observed 2026-08-28T04:03:23.900520+00:00)

## What it is
Cornac is a Python framework for building and comparing multimodal recommender systems, with convenient support for auxiliary data such as item text, images, and social networks. It enables fast experiments and straightforward implementation of new recommendation models, integrating with TensorFlow and PyTorch.

## Use cases
- compare recommender system algorithms on benchmark datasets
- build a collaborative filtering recommender with matrix factorization
- train a recommender using item text and image side information
- evaluate and reproduce recommendation algorithm results
- implement a new recommendation model for research
- benchmark BPR and other RecSys baselines

## When to choose
- you need a well-regarded framework for reproducible recommender experiments
- your models leverage auxiliary multimodal data like text, images, or social graphs
- you want easy integration with TensorFlow or PyTorch
- you need trustworthy baseline implementations for RecSys comparison

## When to avoid
- you need production recommendation serving rather than experimentation
- your use case is general machine learning outside recommendation
- you require a non-Python stack

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, benchmarking, data-science
- domain: machine-learning, data-science
- platform: python, cross-platform
- tags: recommender-systems, collaborative-filtering, matrix-factorization, multimodal-learning, recommendation-algorithms, evaluation-framework, algorithms

## Member repositories
- PreferredAI/cornac (main) score 96

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:23.900520+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 2026-08-30T06:59:19.707329+00:00, confidence not recorded.
  - readme: https://github.com/PreferredAI/cornac (fetched 2026-08-28T04:03:23.900520+00:00, sha c2bf5a41043e)
- Data as of 2026-08-30T08:39:29.467469+00:00.