unit8co/darts

A python library for user-friendly forecasting and anomaly detection on time series.

87
/ 100
Verified

Supports both classical (ARIMA, exponential smoothing) and deep learning models (N-BEATS, TCN) with a unified scikit-learn-style API, enabling seamless model comparison and ensemble techniques. Built-in support for probabilistic forecasting, multivariate time series, past/future covariates, and hierarchical reconciliation. Integrates PyOD for anomaly scoring and wraps forecasting models as anomaly detectors through residual analysis.

9,248 stars and 346,646 monthly downloads. Used by 2 other packages. Actively maintained with 14 commits in the last 30 days. Available on PyPI.

Maintenance 20 / 25
Adoption 22 / 25
Maturity 25 / 25
Community 20 / 25

How are scores calculated?

Stars

9,248

Forks

989

Language

Python

License

Apache-2.0

Last pushed

Mar 07, 2026

Monthly downloads

346,646

Commits (30d)

14

Dependencies

16

Reverse dependents

2

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/unit8co/darts"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.