microsoft/TimeCraft

Official code for TimeCraft: A Time Series Generation Framework for Real-World Applications

52
/ 100
Established

TimeCraft helps scientists, analysts, and researchers generate realistic, synthetic time series data for various applications like healthcare, finance, and energy. It takes a few sample time series, text descriptions, or a downstream task model as input and produces high-quality, controlled synthetic data. This is useful for overcoming data scarcity, protecting privacy, and simulating scenarios without risk.

1,060 stars.

Use this if you need to create realistic time series data across different domains, want to control the characteristics of the generated data using text, or need synthetic data specifically optimized to improve a downstream task like forecasting or anomaly detection.

Not ideal if you only need to analyze existing real-world time series data and have no need for synthetic data generation.

healthcare-analytics financial-modeling energy-forecasting transportation-planning data-privacy
No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

1,060

Forks

64

Language

Python

License

MIT

Last pushed

Feb 12, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/microsoft/TimeCraft"

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