ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works with Claude Code, Codex, OpenClaw, or any LLM agent.
wanshuiyin/Auto-claude-code-research-in-sleep is drawing steady momentum at +58.6 stars/day (92nd percentile in the tracked cohort), for a momentum score of 80.5/100. A recent release is helping fuel the run.
Reconstructed from 269 snapshots — the time-series GitHub’s API doesn’t expose.
~68 forks/day, 7.5× the trailing baseline.
~26 forks/day, 4.5× the trailing baseline.
~11 forks/day, 3.1× the trailing baseline.
Live score, refreshed every 6 hours. Links back to this page.
[](https://repoclimb.com/repo/wanshuiyin/Auto-claude-code-research-in-sleep)Elevated breakout odds over the next 14 days, led by star acceleration (89th pctl) and star velocity (92th pctl). Confidence is high given the available history.
Transparent heuristic · logged for model training
Percentile rank within the tracked cohort. The score self-calibrates — it answers “accelerating vs. everything else,” not raw size.
Release count rose to 46.
~18 forks/day, 4.5× the trailing baseline.
Release count rose to 45.
~11 forks/day, 21.2× the trailing baseline.
Release count rose to 44.
Release count rose to 43.
Release count rose to 42.
~13 forks/day, 5.0× the trailing baseline.
~10 forks/day, 23.0× the trailing baseline.