# jfkirk/tensorrec

A TensorFlow recommendation algorithm and framework in Python.

Repository: https://github.com/jfkirk/tensorrec
Canonical: https://ross.abutalabs.com/products/tensorrec
Language: Python
License: Apache-2.0
License Family: permissive
Topics: machine-learning, tensorflow, recommendation-system, python, recommender-system, recommendation-algorithm, framework
Last push: 2023-05-22T21:34:54+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": 3473, "days_push": 1199, "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 1299, forks 220 (observed 2026-08-28T04:04:17.435076+00:00)

## What it is
TensorRec is a Python framework built on TensorFlow for developing and customizing recommendation algorithms. It handles data manipulation, scoring, and ranking while letting users customize representation/embedding and loss functions.

## Use cases
- build a recommender system in Python
- train collaborative filtering models with TensorFlow
- customize embedding and loss functions for recommendations
- rank items for users based on interaction data
- evaluate recall at k for a recommendation model

## When to choose
- you need a TensorFlow-based recommendation framework with customizable loss and embedding functions
- you want a simple pip-installable library for learning recommender systems
- your project already uses TensorFlow 1.x

## When to avoid
- you need a maintained library - TensorRec is no longer under active development
- you use TensorFlow 2.x or newer APIs
- you need production-grade recommender systems with active community support

## Facets
- artifact type: library
- maturity: abandoned
- function: machine-learning
- domain: machine-learning
- platform: python
- tags: recommender-system, tensorflow, collaborative-filtering, ranking, recommendation-systems

## Member repositories
- jfkirk/tensorrec (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:17.435076+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 2026-08-30T04:53:26.083908+00:00, confidence not recorded.
  - readme: https://github.com/jfkirk/tensorrec (fetched 2026-08-28T04:04:17.435076+00:00, sha 9f8d4431c4bd)
  - registry_pypi: https://pypi.org/pypi/tensorrec/json (fetched 2026-08-29T12:10:01.142052+00:00, sha 5ff00869a33a)
- Data as of 2026-08-30T08:39:29.467469+00:00.