sintel-dev/sigllm

Using Large Language Models for Time Series Anomaly Detection

65
/ 100
Established

This project helps operations engineers, data analysts, or researchers quickly identify unusual patterns in their time-series data. You feed it a timestamped sequence of measurements, and it tells you where anomalies occur. This tool is designed for anyone needing to spot unexpected shifts or events in streams of data, like system metrics, sensor readings, or financial data.

Used by 1 other package. Available on PyPI.

Use this if you need to automatically find unusual segments or spikes in your time-series data, leveraging the latest AI models without deep expertise in machine learning.

Not ideal if you need a simple, explainable anomaly detection method or if your time-series data is not clearly timestamped with corresponding values.

operations-monitoring sensor-data-analysis financial-surveillance system-health data-quality
Maintenance 10 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 20 / 25

How are scores calculated?

Stars

85

Forks

27

Language

Jupyter Notebook

License

MIT

Last pushed

Mar 12, 2026

Commits (30d)

0

Dependencies

11

Reverse dependents

1

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/sintel-dev/sigllm"

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