Foundation Model Python Packages

synthefy-nori

Open-source tabular foundation model for fast, training-free regression with predictive distributions.

ultrams

UltraMS pretrained MS/MS models, PyTorch fine-tuning, and pretraining code

scgpt

Large-scale generative pretrain of single cell using transformer.

lightpfn

LightPFN: a 4.6M-parameter tabular foundation classifier trained only on synthetic data, Apache 2.0, CPU/CUDA/ROCm/Vulkan.

moozy

[ECCV 2026] A Patient-First Foundation Model for Computational Pathology

loopquest

A Production Tool for Embodied AI

spatialformer

The spatial representation learning for single-cell spatial transcriptomics

deepspotm

Multimodal foundation model predicting transcriptome-wide virtual spatial transcriptomics from histology.

segmate

SegMate: A Segmentation Toolkit

synthefy-tabular

Open-source tabular foundation model for fast, training-free regression with predictive distributions.

nanoforecast

World's most deployable time series foundation model — 200K-6.5M params, zero-shot forecasting, streaming RNN inference, ONNX edge deployment, runs on Raspberry Pi

guardrails-ct

Adding guardrails to large language models.

trident-test

Toolkit for large-scale whole-slide image processing.

naturalminer

Mine data for patterns described in natural language