Galaxy-Dawn/claude-scholar — GitHub trend

FINDING #2485 · UNIT ID 1143237475

Galaxy-Dawn/claude-scholar

Semi-automated research assistant for academic research and software development. Supports Claude Code, Codex CLI, Kimi Code CLI, and OpenCode across ideation, coding, experiments, writing, and publication.

[ PYTHON ][ GITHUB ↗ ]

SURPRISE SCORE

0.00

Score Breakdown

SURPRISE0.0193

ENGAGEMENT0.25

FRESHNESS1.00

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

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

2% OF STARS IN ARCHIVE

Growth Telemetry

VELOCITY /D

13.86

ACCEL

-0.36

RETENTION

64.3%

PEAK 2026-08-25 · FORK-RETENTION 0.0% · 97 STARS / WINDOW

Author Audience

AUDIENCE

677

FOLLOWERS

118

OWNER ★

5,588

Engagement Signals

FORKS

417

ISSUE AUTH

PR AUTH

UNIQUE STARGAZERS 97 / 97 (DIVERSITY 1.00)

Why This Is A Finding

Galaxy-Dawn/claude-scholar собрал 97 звёзд за окно, тогда как у автора всего 118 подписчиков — эффективная аудитория ≈ 677. Это даёт surprise-индекс 0.0193 (звёзды относительно охвата автора, а не в абсолюте). Удержание форков 0.0% и 0 внешних контрибьюторов отделяют реальный инструмент от разовой вспышки. Акселерация отрицательная — внимание остывает после пика.

Related Findings

RANKS ABOVE 75% OF 9771 FINDINGS

#05MddIdd/mdd-sim-gateway[ PYTHON ]0.41 #08zeenie-ai/OpenCompany[ PYTHON ]0.38 #15litaolemo/xtquant_big_convert[ PYTHON ]0.33 #23917Dhj/DeepPaperNote[ PYTHON ]0.27 #24LBH-123-AI/Comfyui_Minimax_h3_latent_Upscaler[ PYTHON ]0.27

METRICS IN CONTEXT

MEDIAN ACROSS ALL 9771 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW

METRICVALUEMEDIANΔ MEDPERCENTILE

SCORE0.010.00+0.00ABOVE 75%

VELOCITY13.863.71+10.14ABOVE 84%

RETENTION64.3%39.3%+24.9 PPABOVE 84%

FORKS41791+326ABOVE 83%

SURPRISE0.020.01+0.01ABOVE 69%