Foundation Models Python Packages

toons

A high-performance TOON (Token Oriented Object Notation) parser and serializer for Python.

neptune-fetcher

Neptune Fetcher is designed to separate data retrieval capabilities from the regular neptune package. This separation makes data fetching more efficient and improves performance.

pyod

A Python library for anomaly detection across tabular, time series, graph, text, and image data. 60+ detectors, benchmark-backed ADEngine orchestration, and an agentic workflow for AI agents.

mattersim

MatterSim: A deep learning atomistic model across elements, temperatures and pressures.

chronos-forecasting

Chronos: Pretrained Models for Time Series Forecasting

neptune-query

Read-only API for fetching metadata tracked with the Neptune logging client.

tabpfn

⚡ TabPFN: Foundation Model for Tabular Data ⚡

nixtla

TimeGPT-1: production ready pre-trained Time Series Foundation Model for forecasting and anomaly detection. Generative pretrained transformer for time series trained on over 100B data points. It's capable of accurately predicting various domains such as retail, electricity, finance, and IoT with just a few lines of code 🚀.

terratorch

A Python toolkit for fine-tuning Geospatial Foundation Models (GFMs).

skforecast

Python library for time series forecasting using scikit-learn compatible models, statistical methods, and foundation models

torchxrayvision

TorchXRayVision: A library of chest X-ray datasets and models. Classifiers, segmentation, and autoencoders.

tabicl

TabICLv2: A state-of-the-art tabular foundation model

osam

Get up and running with SAM1,2,3, EfficientSAM, YOLO-World, and other promptable vision models locally.

tabpfn-client

⚡ Easy API access to the tabular foundation model TabPFN ⚡

microsoft-aurora

Implementation of the Aurora model for Earth system forecasting

colossalai

Making large AI models cheaper, faster and more accessible

tirex-ts

TiRex: Zero-Shot Forecasting Across Long and Short Horizons with Enhanced In-Context Learning

autodistill

Images to inference with no labeling (use foundation models to train supervised models).

meds-reader

A high-performance database and Python reader interface for MEDS datasets

helical

A framework for state-of-the-art pre-trained bio foundation models on genomics and transcriptomics modalities.

py-data-juicer

Data processing for and with foundation models! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷

nixtlats

TimeGPT-1: production ready pre-trained Time Series Foundation Model for forecasting and anomaly detection. Generative pretrained transformer for time series trained on over 100B data points. It's capable of accurately predicting various domains such as retail, electricity, finance, and IoT with just a few lines of code 🚀.

ado-core

A framework for designing, executing and analysing experiment campaigns

timecopilot-chronos-forecasting

Chronos: Pretrained Models for Time Series Forecasting