News Summary

• Run controlled, reproducible ML experiments on your existing pipelines.
• You define a domain — a research area pointing at your data with a fixed evaluation contract.
• An AI agent runs experiments inside that contract: writing training code, calling frozen load_data and evaluate tools, logging metrics, and recording findings as durable knowledge atoms.
• Dojo generalises that pattern to any well-defined ML problem class.
• Open source.
• Single-tenant, local-first, by design.
• The package on PyPI is dojoml; the CLI binary it installs is dojo.