#3737th of 37 in ML frameworks and libraries
recommenders
Python recommender-system library with notebooks for classic and deep learning models
- Stars
- 21.9k
- License
- MIT
- Last commit
- Sep 2026
- Last release
- Dec 2024
- Language
- Python
Missed the latest GitHub check; these facts may be older.
Overview
Recommenders is a Python package and set of Jupyter notebooks for building, evaluating and tuning recommendation models. It includes about 30 algorithms (ALS, SAR, NCF, LightGCN, SASRec, xDeepFM, BPR, VAEs and others), plus utilities for dataset loading, train/test splitting and offline metrics. It is a Linux Foundation AI & Data project and ships a MovieLens benchmark notebook.
Who it is for: Data scientists and ML engineers prototyping and benchmarking recommenders
Strengths
- About 30 algorithms, each with a quick-start or deep-dive notebook
- Includes data splitters, loaders and offline metrics (MAP, nDCG, precision, recall, RMSE)
- Benchmark notebook compares algorithms on MovieLens 100k with reported results
- Core package installs with pip or uv and runs all CPU notebooks
Weaknesses
- Not a serving system; the operationalization example targets Azure only
- Spark and GPU models need extra installs via [spark] or [gpu] extras
- Some models sit under an [experimental] extra and are not thoroughly tested
- Last release 1.2.1 (Dec 2024); no LLM-based recommenders listed
What it needs
- GPU optional
- Needs Python 3.11, gcc, Jupyter, PySpark (optional)
- Models: ALS, SAR, NCF, LightGCN, SASRec
Also in ML frameworks and libraries
See all 37| Rank | Project | Score |
|---|---|---|
| 1 | transformersPython library defining open models for text, vision, audio and multimodal tasks | 95 out of 100 |
| 2 | pytorchPython tensor library with GPU support and tape-based autograd for deep learning | 94 out of 100 |
| 3 | ultralyticsPython library and CLI for training and running YOLO vision models | 90 out of 100 |
| #4 | supervisionPython toolkit for loading, annotating and counting computer vision detections | 87 out of 100 |
| #5 | pytorch-image-modelsPyTorch library of image models, pretrained weights and reference training scripts | 86 out of 100 |