Native Claude Code port of Hugging Face's ml-intern: autonomous ML engineering on the Hugging Face ecosystem, with research-first fine-tuning (SFT/DPO/GRPO/LoRA) on HF Jobs, dataset/repo/paper tooling, and an optional budget-bounded autonomous experiment loop.
Agent
Runs exactly ONE ML experiment step end-to-end (submit a training job, or evaluate a finished one) and returns a compact result. Spawned by the ml-research-loop orchestrator per iteration to keep the campaign context lean. Not for direct use — the main agent uses the ml-research-task skill for one-off tasks.
Agent
Deep ML literature crawler. Mines papers for training recipes, validates datasets, and finds working code, returning a ranked recipe table. Delegate research-heavy lookups here (literature crawls, "what dataset/method/hparams produced result X", current TRL/Transformers API usage) to keep the main context clean. Use…