#8585th of 105 in ML frameworks and libraries
hyperopt
Python library for hyperparameter search over conditional, mixed search spaces
- Stars
- 7.6k
- License
- custom license
- Last commit
- Jul 2026
- Last release
- Jul 2026
- Language
- Python
7,522 on 1 Apr 20267,597 on 21 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Hyperopt is a Python library that minimizes an objective function over search spaces with real-valued, discrete and conditional dimensions. It implements random search, Tree of Parzen Estimators (TPE) and Adaptive TPE, and can parallelize evaluations through Apache Spark or MongoDB. The README states no RAM or GPU requirements.
Who it is for: ML engineers tuning hyperparameters in Python, serially or on Spark/MongoDB
Strengths
- Search spaces can nest conditional branches, as in the hp.choice example
- Three algorithms: random search, TPE and Adaptive TPE
- Parallel evaluation via SparkTrials or MongoTrials extras
- Installs from PyPI with pip or uv; fmin API is small
Weaknesses
- Gaussian-process and regression-tree optimizers are designed for but not implemented
- Documentation is split between a docs site and the GitHub wiki
- Parallel runs need an external Spark cluster or MongoDB server
- License is not identified automatically (NOASSERTION)
What it needs
- no GPU
- Needs Apache Spark (optional), MongoDB (optional)
Also in ML frameworks and libraries
See all 105| Rank | Project | Score |
|---|---|---|
| 1 | transformersPython library defining open models for text, vision, audio and multimodal tasks | 94 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 | 93 out of 100 |
| #4 | pytorch-image-modelsPyTorch library of image models, pretrained weights and reference training scripts | 92 out of 100 |
| #5 | supervisionPython toolkit for loading, annotating and counting computer vision detections | 91 out of 100 |