# facebookresearch/Kats

Kats, a kit to analyze time series data, a lightweight, easy-to-use, generalizable, and extendable framework to perform time series analysis, from understanding the key statistics and characteristics, detecting change points and anomalies, to forecasting future trends.

Repository: https://github.com/facebookresearch/Kats
Canonical: https://ross.abutalabs.com/products/kats
Language: Python
License: MIT
License Family: permissive
Last push: 2026-08-19T01:26:53+00:00

## Health v2 (maintenance only)
Score: 67/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 98, release rhythm 8, longevity 100
- inputs: {"age_days": 2015, "days_push": 15, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 6460, forks 637 (observed 2026-08-28T04:09:43.603242+00:00)

## What it is
Kats is a Python toolkit from Facebook's Infrastructure Data Science team for time series analysis, covering statistics, anomaly and change point detection, forecasting, and feature extraction. It provides a unified TimeSeriesData abstraction and models like Prophet in a lightweight, extensible framework.

## Use cases
- forecast future trends in time series data
- detect anomalies in metrics over time
- detect change points in a time series
- extract features and embeddings from time series
- analyze key statistics of time series data
- perform multivariate time series analysis in python

## When to choose
- you need a one-stop Python toolkit for detection, forecasting, and feature extraction on time series
- you want a simple unified API (TimeSeriesData) over multiple forecasting models like Prophet
- you are doing data science work on business metrics and trends

## When to avoid
- you need real-time streaming time series processing at scale
- you need deep-learning-based forecasting with GPU acceleration
- you want a very actively developed library with frequent updates

## Facets
- artifact type: library
- maturity: maintenance
- function: data-science, machine-learning, analytics
- domain: data-science, time-series, analytics
- platform: python, cross-platform
- tags: time-series-analysis, forecasting, anomaly-detection, change-point-detection, feature-extraction, prophet

## Member repositories
- facebookresearch/Kats (main) score 67

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:43.603242+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:44:37.751744+00:00, confidence not recorded.
  - readme: https://github.com/facebookresearch/Kats (fetched 2026-08-28T04:09:43.603242+00:00, sha 05a71ac6dacd)
  - registry_pypi: https://pypi.org/pypi/kats/json (fetched 2026-08-29T08:41:12.166305+00:00, sha 4ec186cdbb21)
- Data as of 2026-08-30T08:39:29.467469+00:00.