Synthefy Releases Nori V1: Open Source Foundation Model Aiming to Replace XGBoost

rohanpaul_ai · x · 2026-08-19

Synthefy has launched Nori V1, an open-source foundation model designed for structured (tabular) data. The platform aims to revolutionize tabular ML by allowing one pretrained model to generalize across different problems without the need for retraining or fine-tuning on new datasets. Nori takes labeled rows as context and produces predictions in a single forward pass, eliminating traditional steps like feature engineering and hyperparameter tuning. The company claims Nori beats tuned XGBoost and has achieved nearly 600,000 downloads. It supports local execution via a Python API.

Related event: Synthefy Raises $6.5M Seed, Open-Sources Tabular Foundation Model Nori(9 posts)→

Original post →

More from Models

Models channel →