> ML_LIBRARIES_CATALOG_v1.0
Qualified ML Libraries
Every library is independently qualified with primary citations, supported version ranges, hardware accelerator separation, and real-world failure patterns.
MediaPipe
Google AI Edge
Google's cross-platform framework for real-time perceptual AI on edge, mobile, and web.
Segment Anything (SAM)
Meta FAIR
Meta's promptable foundation model for zero-shot image and video segmentation.
statsmodels
statsmodels Developers / NumFOCUS
The premier Python library for rigorous statistical inference and classical econometrics.
Prophet
Meta Open Source
Meta's automated forecasting tool optimized for business metrics and human-interpretable seasonality.
sktime
sktime community / NumFOCUS
Unified scikit-learn compatible toolbox for time series forecasting, classification, and clustering.
Darts
Unit8
User-friendly Python library for time series forecasting with classical and deep learning models.
GluonTS
Amazon Web Services (AWS)
AWS's toolkit for probabilistic deep learning time series modeling and Chronos foundation models.
StatsForecast
Nixtla
Lightning-fast statistical time series forecasting for millions of series using Numba.
MLForecast
Nixtla
Scalable machine learning time series forecasting using gradient boosting and automated feature engineering.
NeuralForecast
Nixtla
Deep learning time series forecasting library implementing modern transformer and MLP architectures in PyTorch.
tsfresh
Blue Yonder / tsfresh developers
Automated feature extraction and hypothesis-driven feature selection for time series.
pmdarima
Taylor G. Smith / alkaline-ml
Python's equivalent of R's auto.arima for automated seasonal ARIMA order selection.
PyMC
PyMC Developers / NumFOCUS
Leading probabilistic programming library for Python with advanced Bayesian inference engines.
CmdStanPy (Stan)
Stan Development Team / NumFOCUS
Python interface to CmdStan for high-performance C++ compiled Bayesian inference.
NumPyro
Pyro Developers / Uber / Broad Institute
High-performance probabilistic programming powered by JAX for GPU/TPU accelerated Bayesian inference.
Pyro
Uber AI / Linux Foundation AI & Data
Deep probabilistic programming library integrating PyTorch neural networks with Bayesian probability.
TensorFlow Probability
Google / TensorFlow Team
Google's probabilistic reasoning and statistical analysis library for TensorFlow and JAX.