wanshuiyin/Auto-claude-code-research-in-sleep — GitHub trend

FINDING #1484 · UNIT ID 1177608268

wanshuiyin/Auto-claude-code-research-in-sleep

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.

[ PYTHON ][ GITHUB ↗ ]

SURPRISE SCORE

0.00

Score Breakdown

SURPRISE0.0298

ENGAGEMENT0.32

FRESHNESS1.00

SCORE = SURPRISE × ENGAGEMENT^0.7 × FRESHNESS × VISIBILITY × CONFIDENCE

SURPRISE = WINDOW STARS / DAYS / (AUDIENCE + FLOOR)

3% OF STARS IN ARCHIVE

Growth Telemetry

VELOCITY /D

59.43

ACCEL

+2.93

RETENTION

40.5%

PEAK 2026-08-25 · FORK-RETENTION 37.5% · 416 STARS / WINDOW

Author Audience

AUDIENCE

1,956

FOLLOWERS

319

OWNER ★

16,397

Engagement Signals

FORKS

1,346

ISSUE AUTH

PR AUTH

UNIQUE STARGAZERS 416 / 416 (DIVERSITY 1.00)

Why This Is A Finding

wanshuiyin/Auto-claude-code-research-in-sleep собрал 416 звёзд за окно, тогда как у автора всего 319 подписчиков — эффективная аудитория ≈ 1,956. Это даёт surprise-индекс 0.0298 (звёзды относительно охвата автора, а не в абсолюте). Удержание форков 37.5% и 0 внешних контрибьюторов отделяют реальный инструмент от разовой вспышки. Акселерация положительная — рост ещё не выдохся.

Related Findings

RANKS ABOVE 85% OF 9760 FINDINGS

#08MddIdd/mdd-sim-gateway[ PYTHON ]0.41 #17litaolemo/xtquant_big_convert[ PYTHON ]0.36 #20LBH-123-AI/Comfyui_Minimax_h3_latent_Upscaler[ PYTHON ]0.34 #24zeenie-ai/OpenCompany[ PYTHON ]0.30 #25917Dhj/DeepPaperNote[ PYTHON ]0.29

METRICS IN CONTEXT

MEDIAN ACROSS ALL 9760 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW

METRICVALUEMEDIANΔ MEDPERCENTILE

SCORE0.010.00+0.01ABOVE 85%

VELOCITY59.433.71+55.71ABOVE 96%

RETENTION40.5%38.0%+2.5 PPABOVE 54%

FORKS1,34686+1,260ABOVE 95%

SURPRISE0.030.01+0.02ABOVE 77%