# salesforce/Merlion

Merlion: A Machine Learning Framework for Time Series Intelligence

Repository: https://github.com/salesforce/Merlion
Canonical: https://ross.abutalabs.com/products/merlion
Language: Python
License: BSD-3-Clause
License Family: permissive
Topics: time-series, anomaly-detection, forecasting, machine-learning, benchmarking, automl, ensemble-learning
Archived: true
Last push: 2026-03-11T12:52:32+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 71, release rhythm 8, longevity 100
- inputs: {"age_days": 1862, "days_push": 175, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4491, forks 358 (observed 2026-08-28T04:08:51.313620+00:00)

## What it is
Merlion is a Python library from Salesforce providing an end-to-end machine learning framework for time series intelligence, covering forecasting, anomaly detection, and change point detection. It unifies data loading, model training, AutoML hyperparameter tuning, post-processing, and benchmarking under a shared API.

## Use cases
- forecast future values of a time series
- detect anomalies in univariate or multivariate time series
- detect change points in streaming metrics
- automatically tune and select time series models with automl
- benchmark forecasting and anomaly detection models across datasets
- forecast with exogenous regressors

## When to choose
- you need a unified Python API for multiple time series tasks like forecasting and anomaly detection
- you want built-in AutoML and sensible default models to get started quickly
- you need standardized benchmarking across many time series datasets

## When to avoid
- you need real-time low-latency production inference at scale
- you only need simple plotting or visualization of time series
- you work outside Python or need GPU-accelerated deep learning training as the primary focus

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, benchmarking, data-science, etl
- domain: time-series, machine-learning, data-science, analytics
- platform: python, cross-platform
- tags: time-series, forecasting, anomaly-detection, change-point-detection, automl, ensemble-learning

## Member repositories
- salesforce/Merlion (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:51.313620+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 2026-08-29T18:20:29.176380+00:00, confidence not recorded.
  - readme: https://github.com/salesforce/Merlion (fetched 2026-08-28T04:08:51.313620+00:00, sha 19a35c9aad09)
- Data as of 2026-08-30T08:39:29.467469+00:00.