# linkedin/luminol

Anomaly Detection and Correlation library

Repository: https://github.com/linkedin/luminol
Canonical: https://ross.abutalabs.com/products/luminol
Language: Python
License: Apache-2.0
License Family: permissive
Topics: anomaly-detection, anomalydetection
Last push: 2025-08-22T23:19:05+00:00

## Health v2 (maintenance only)
Score: 49/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 38, release rhythm 35, longevity 100
- inputs: {"age_days": 3941, "days_push": 376, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1230, forks 217 (observed 2026-08-28T04:04:03.780141+00:00)

## What it is
Luminol is a lightweight Python library for time series analysis that provides anomaly detection and correlation between time series. It assigns anomaly scores to data points without predefined thresholds and supports correlating shifted peaks to help identify root causes of anomalies.

## Use cases
- detect anomalies in time series data
- find correlation between two time series
- automate root cause analysis of metric spikes
- rank correlated system metrics during an incident
- identify time windows where anomalies occurred

## When to choose
- you need lightweight, threshold-free anomaly detection in Python
- you want to correlate a detected anomaly with other metrics for root cause analysis
- you need configurable detection algorithms with anomaly severity scores

## When to avoid
- you need real-time streaming anomaly detection at scale
- you need deep learning based forecasting or multivariate models
- you need actively developed features beyond the 0.4 release

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, analytics, monitoring
- domain: data-science, analytics, monitoring, time-series
- platform: python, cross-platform
- tags: anomaly-detection, time-series-analysis, correlation, root-cause-analysis

## Member repositories
- linkedin/luminol (main) score 49

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:03.780141+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 2026-08-30T06:15:02.780817+00:00, confidence not recorded.
  - readme: https://github.com/linkedin/luminol (fetched 2026-08-28T04:04:03.780141+00:00, sha 19b0a55f2b59)
  - registry_pypi: https://pypi.org/pypi/luminol/json (fetched 2026-08-29T12:22:44.928376+00:00, sha 90835f5cf19f)
- Data as of 2026-08-30T08:39:29.467469+00:00.