neo4j-labs/llm-graph-builder — GitHub trend

◂ BACK TO LEADERBOARD

FINDING #5483 · UNIT ID 741989385

neo4j-labs/llm-graph-builder

Neo4j graph construction from unstructured data using LLMs

[ JUPYTER NOTEBOOK ][ ORG ][ VERIFIED ][ GITHUB ↗ ]

SURPRISE SCORE

0.00

Score Breakdown

SURPRISE0.00238

ENGAGEMENT0.46

FRESHNESS1.45

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

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

4% OF STARS IN ARCHIVE

Growth Telemetry

VELOCITY /D

7.13

ACCEL

-0.27

RETENTION

7.7%

PEAK 2026-08-08 · FORK-RETENTION 68.6% · 214 STARS / WINDOW

Author Audience

AUDIENCE

2,957

FOLLOWERS

347

OWNER ★

9,120

Engagement Signals

FORKS

882

ISSUE AUTH

PR AUTH

UNIQUE STARGAZERS 214 / 214 (DIVERSITY 1.00)

Why This Is A Finding

neo4j-labs/llm-graph-builder собрал 214 звёзд за окно, тогда как у автора всего 347 подписчиков — эффективная аудитория ≈ 2,957. Это даёт surprise-индекс 0.00238 (звёзды относительно охвата автора, а не в абсолюте). Удержание форков 68.6% и 0 внешних контрибьюторов отделяют реальный инструмент от разовой вспышки. Акселерация отрицательная — внимание остывает после пика.

Related Findings

RANKS ABOVE 43% OF 9591 FINDINGS

#195xbsheng/atguigu-note[ JUPYTER NOTEBOOK ]0.0835 #329lyogavin/airllm[ JUPYTER NOTEBOOK ]0.0381 #347gmonce/scikit-learn-book[ JUPYTER NOTEBOOK ]0.0371 #564raiyanyahya/how-to-train-your-gpt[ JUPYTER NOTEBOOK ]0.029 #874Mengmouxu/SceneGen[ JUPYTER NOTEBOOK ]0.0224

METRICS IN CONTEXT

MEDIAN ACROSS ALL 9591 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW

METRICVALUEMEDIANΔ MEDPERCENTILE

SCORE0.000.00-0.00ABOVE 43%

VELOCITY7.133.63+3.50ABOVE 72%

RETENTION7.7%24.8%-17.2 PPABOVE 17%

FORKS882120+762ABOVE 89%

SURPRISE0.000.01-0.01ABOVE 24%