Github Trends®
9760 findingsmedian surprise 0.0099window 7 days
UNIT / TREND-MONITOR · REV 2.6
[ 7 days window ]
SOURCE: own snapshots
FINDING #3870 · UNIT ID 1129786550
teng-lin/notebooklm-py
Unofficial Python API and agentic skill for Google Gemini Notebook. Full programmatic access to NotebookLM's features—including capabilities the web UI doesn't expose—via Python, CLI, and AI agents like Claude Code, Codex, and OpenClaw.
[ PYTHON ][ GITHUB ↗ ]
SURPRISE SCORE
0.00

Score Breakdown

SURPRISE0.00748
ENGAGEMENT0.42
FRESHNESS1.00
SCORE = SURPRISE × ENGAGEMENT^0.7 × FRESHNESS × VISIBILITY × CONFIDENCE
SURPRISE = WINDOW STARS / DAYS / (AUDIENCE + FLOOR)
1% OF STARS IN ARCHIVE

Growth Telemetry

VELOCITY /D
20.00
ACCEL
-0.79
RETENTION
45.0%
PEAK 2026-08-26 · FORK-RETENTION 10.5% · 140 STARS / WINDOW

Author Audience

AUDIENCE
2,635
FOLLOWERS
704
OWNER ★
19,309

Engagement Signals

FORKS
2,557
ISSUE AUTH
0
PR AUTH
0
UNIQUE STARGAZERS 140 / 140 (DIVERSITY 1.00)

Why This Is A Finding

teng-lin/notebooklm-py собрал 140 звёзд за окно, тогда как у автора всего 704 подписчиков — эффективная аудитория ≈ 2,635. Это даёт surprise-индекс 0.00748 (звёзды относительно охвата автора, а не в абсолюте). Удержание форков 10.5% и 0 внешних контрибьюторов отделяют реальный инструмент от разовой вспышки. Акселерация отрицательная — внимание остывает после пика.

METRICS IN CONTEXT

MEDIAN ACROSS ALL 9760 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW
METRICVALUEMEDIANΔ MEDPERCENTILE
SCORE0.000.00+0.00ABOVE 60%
VELOCITY20.003.71+16.29ABOVE 88%
RETENTION45.0%38.0%+7.0 PPABOVE 61%
FORKS2,55786+2,471ABOVE 97%
SURPRISE0.010.01-0.00ABOVE 42%