HPC ODA Commons: Community-Governed Contracts and Toolkit for Reproducible Operational Data Analytics

High-Performance Computing (HPC) facilities generate vast quantities of operational data, yet turning this data into actionable insight remains hindered by fragmented, site-specific analytics pipelines. Results from one site cannot easily be compared with another, and promising methods stay siloed because there is no shared language for describing the data, the experiments, or the outcomes. We present HPC ODA Commons, an open-source, CLI-first toolkit that establishes community-governed contracts in the form of versioned schemas, canonical artifacts, and benchmark recipes for HPC Operational Data Analytics (ODA). The toolkit ingests heterogeneous site-specific data into a standardized format, evaluates predictive models through reproducible recipe-driven benchmarks, and can aggregate results into leaderboards for cross-site comparison, all without requiring data to leave the local cluster. Version 0.1 targets job runtime prediction, shipping three models: a mean-prediction baseline, an XGBoost model with rolling-window evaluation, and a TF-IDF + kNN text-similarity model. We describe the architecture, demonstrate results on two supercomputer datasets totaling 13 million jobs, and show how the toolkit's structured, declarative design makes it well-suited to operation by AI coding agents. HPC ODA Commons is available as open-source software under a BSD-3-Clause license.