moment-timeseries-foundation-model/TimeSeriesGym

Official code for TimeSeriesGym: A Scalable Benchmark for (Time Series) Machine Learning Engineering Agents

39
/ 100
Emerging

TimeSeriesGym helps machine learning engineers and researchers rigorously test and compare AI agents designed to solve time series problems. It takes diverse time series datasets and agent code as input, then evaluates how well the agents perform on tasks like data preprocessing, model tuning, and code migration across 33 different challenges. This is for professionals building or researching automated machine learning systems for time series analysis.

Use this if you are a machine learning engineer or researcher developing, evaluating, or benchmarking AI agents for various time series machine learning engineering tasks.

Not ideal if you are looking for a tool to directly build or deploy time series models for end-user applications, rather than evaluating the agents that build them.

time-series-analysis machine-learning-engineering AI-agent-evaluation model-benchmarking data-preprocessing
No Package No Dependents
Maintenance 6 / 25
Adoption 7 / 25
Maturity 15 / 25
Community 11 / 25

How are scores calculated?

Stars

34

Forks

4

Language

Python

License

MIT

Last pushed

Nov 30, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/moment-timeseries-foundation-model/TimeSeriesGym"

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