openags/paper-search-mcp — GitHub trend

◂ BACK TO LEADERBOARD

FINDING #1491 · UNIT ID 961295208

openags/paper-search-mcp

MCP, CLI, Skills for searching and downloading academic papers from multiple sources like arXiv, PubMed, bioRxiv, etc.

[ PYTHON ][ ORG ][ GITHUB ↗ ]

SURPRISE SCORE

0.00

Score Breakdown

SURPRISE0.0191

ENGAGEMENT0.20

FRESHNESS1.39

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

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

15% OF STARS IN ARCHIVE

Growth Telemetry

VELOCITY /D

10.80

ACCEL

-0.08

RETENTION

46.6%

PEAK 2026-06-22 · FORK-RETENTION 0.0% · 324 STARS / WINDOW

Author Audience

AUDIENCE

527

FOLLOWERS

OWNER ★

2,323

Engagement Signals

FORKS

209

ISSUE AUTH

PR AUTH

UNIQUE STARGAZERS 324 / 324 (DIVERSITY 1.00)

Why This Is A Finding

openags/paper-search-mcp собрал 324 звёзд за окно, тогда как у автора всего 31 подписчиков — эффективная аудитория ≈ 527. Это даёт surprise-индекс 0.0191 (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 76% OF 6295 FINDINGS

#01shy3130/tickflow-stock-panel[ PYTHON ]0.46 #06Panniantong/Agent-Reach[ PYTHON ]0.29 #10sums001/Windows-Copilot-API[ PYTHON ]0.27 #12HUANGCHIHHUNGLeo/claude-real-video[ PYTHON ]0.24 #14realiti4/claude-swap[ PYTHON ]0.21

METRICS IN CONTEXT

MEDIAN ACROSS ALL 6295 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW

METRICVALUEMEDIANΔ MEDPERCENTILE

SCORE0.010.00+0.01ABOVE 76%

VELOCITY10.804.23+6.57ABOVE 76%

RETENTION46.6%29.4%+17.2 PPABOVE 81%

FORKS20992+117ABOVE 70%

SURPRISE0.020.01+0.01ABOVE 64%