moment-timeseries-foundation-model/TimeSeriesGym
Official code for TimeSeriesGym: A Scalable Benchmark for (Time Series) Machine Learning Engineering Agents
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.
Stars
34
Forks
4
Language
Python
License
MIT
Category
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.
Higher-rated alternatives
ai4co/reevo
[NeurIPS 2024] ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolution
SALT-NLP/collaborative-gym
Framework and toolkits for building and evaluating collaborative agents that can work together...
Gen-Verse/LatentMAS
Latent Collaboration in Multi-Agent Systems
lean-dojo/LeanCopilot
LLMs as Copilots for Theorem Proving in Lean
WooooDyy/AgentGym-RL
Code and implementations for the paper "AgentGym-RL: Training LLM Agents for Long-Horizon...