Research
Work on the infrastructure, methods, and open questions of AI research — reproducibility, agentic workflows, and open evaluation.
Release
TSEval: an open leaderboard you can check
TSEval is an open, reproducible leaderboard for time-series forecasting. Every row is rebuilt from a community submission — a full experiment trajectory and a verified result you can open, audit, and reproduce — not a number pasted into a table. The live board is at tseval.diaugeia.ai.
Diaugeia.AI team
Release
ModernTSF: time-series research infrastructure built for AI agents
170+ ready-to-run models, 60+ datasets, and a full set of agent skills. Clone the repo, open Claude Code or Codex, and say what you want — the infrastructure handles the rest.
Diaugeia.AI team