Custom APRL machine-learning algorithm + a curated ML knowledge base of 923 papers, lectures, and explainers. NumPy classifier/regressor, tests, benchmarks, provenance, Obsidian, and agent-ready Markdown.
2 files for Codex, OpenCode and Claude Code: machine-learning-library AGENTS.md, machine-learning-library CLAUDE.md — 1,399 tokens loaded in every session.
AGENTS.md A 1,150 tok CLAUDE.md A 249 tok These files are ATOM00blue/machine-learning-library's own configuration — they tell Codex, OpenCode and Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.