A self-improving ML agent that compounds capability across projects through knowledge crystallization, reusable skills and shared ML/MLOps infrastructure.
Latest release v0.11.0 — v0.11.0 — Ontology Upgrade: Experiment IR · Decision Trace · Capability Governance · 9 Oct 2026
1 file for Codex and OpenCode: cultivating-ml-agent AGENTS.md — 3,602 tokens loaded in every session.
AGENTS.md A 3,602 tok These files are topprismdata/cultivating-ml-agent's own configuration — they tell Codex and OpenCode 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.