moment-timeseries-foundation-model/moment
MOMENT: A Family of Open Time-series Foundation Models, ICML'24
This project offers a powerful tool for analyzing time-series data across many different fields. It takes your raw time-series measurements (like stock prices, sensor readings, or health metrics) and can either fill in missing data, spot unusual patterns, classify events, or predict future values. Anyone working with sequential data—such as financial analysts, IoT engineers, or medical researchers—can use it to gain insights with minimal effort.
723 stars.
Use this if you need to quickly get accurate predictions, identify anomalies, or classify patterns within various types of time-series data, even with limited historical examples for your specific task.
Not ideal if your primary goal is to analyze non-sequential, static datasets or if you require extensive, human-interpretable explanations for every decision made by the model.
Stars
723
Forks
101
Language
TypeScript
License
MIT
Category
Last pushed
Feb 10, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/moment-timeseries-foundation-model/moment"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related models
amazon-science/chronos-forecasting
Chronos: Pretrained Models for Time Series Forecasting
SalesforceAIResearch/uni2ts
Unified Training of Universal Time Series Forecasting Transformers
ServiceNow/TACTiS
TACTiS-2: Better, Faster, Simpler Attentional Copulas for Multivariate Time Series, from...
yotambraun/APDTFlow
APDTFlow is a modern and extensible forecasting framework for time series data that leverages...
Thinklab-SJTU/Crossformer
Official implementation of our ICLR 2023 paper "Crossformer: Transformer Utilizing...