domains / families / research / run-experiment
Deploy and run ML experiments on local or remote GPU servers. Use when user says "run experiment", "deploy to server", "跑实验", or needs to launch training jobs. Deploy and run ML experiments on local, remote, Vast.ai, or Modal serverless GPU. Use when user says "run experiment", "deploy to server", "跑实验", or needs to launch training jobs.
The two copies share the same core workflow (detect environment, pre-flight GPU check, sync code, optional W&B, deploy, verify), but the wanshuiyin/Auto-claude-code-research-in-sleep copy adds a Modal serverless path, an environment contract with spec-hash warm-reuse and a seeded kernel witness, and ordered pip install phases. The brycewang-stanford/Auto-Empirical-Research-Skills copy is a shorter mirror that omits Modal and the env contract, and uses a simpler requirements.txt install. Crowning one would hide the Modal and env-contract steps, so the copies should be combined.