vfeofanov/mantis
Mantis: Lightweight Calibrated Foundation Model for User-Friendly Time Series Classification
Mantis helps you categorize sequences of measurements over time, such as sensor readings or financial market data, even with limited historical examples. It takes your raw time series data and outputs labels or probabilities for what category each series belongs to. This is ideal for analysts, researchers, or operations managers who need to automatically classify patterns in time-dependent information.
105 stars.
Use this if you need to reliably categorize time series data, especially when you have a small amount of labeled data, or you're dealing with complex multi-channel sensor readings.
Not ideal if your data is not a time series, or if you need to predict future values rather than classify past patterns.
Stars
105
Forks
8
Language
Jupyter Notebook
License
Apache-2.0
Category
Last pushed
Mar 02, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/vfeofanov/mantis"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
amazon-science/chronos-forecasting
Chronos: Pretrained Models for Time Series Forecasting
SalesforceAIResearch/uni2ts
Unified Training of Universal Time Series Forecasting Transformers
moment-timeseries-foundation-model/moment
MOMENT: A Family of Open Time-series Foundation Models, ICML'24
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...