OSU-NLP-Group/HippoRAG — GitHub trend

FINDING #7073 · UNIT ID 805115184

OSU-NLP-Group/HippoRAG

[NeurIPS'24] HippoRAG is a novel RAG framework inspired by human long-term memory that enables LLMs to continuously integrate knowledge across external documents. RAG + Knowledge Graphs + Personalized PageRank.

[ PYTHON ][ ORG ][ GITHUB ↗ ]

SURPRISE SCORE

0.00

Score Breakdown

SURPRISE0.00102

ENGAGEMENT0.34

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

3.29

ACCEL

+0.18

RETENTION

47.6%

PEAK 2026-08-08 · FORK-RETENTION 0.0% · 23 STARS / WINDOW

Author Audience

AUDIENCE

3,181

FOLLOWERS

473

OWNER ★

11,174

Engagement Signals

FORKS

418

ISSUE AUTH

PR AUTH

UNIQUE STARGAZERS 23 / 23 (DIVERSITY 1.00)

Why This Is A Finding

OSU-NLP-Group/HippoRAG собрал 23 звёзд за окно, тогда как у автора всего 473 подписчиков — эффективная аудитория ≈ 3,181. Это даёт surprise-индекс 0.00102 (звёзды относительно охвата автора, а не в абсолюте). Удержание форков 0.0% и 0 внешних контрибьюторов отделяют реальный инструмент от разовой вспышки. Акселерация положительная — рост ещё не выдохся.

Related Findings

RANKS ABOVE 27% OF 9726 FINDINGS

#03NikoDemon80/ComfyUI-H3-Motion-Context[ PYTHON ]0.49 #04semantica-agi/semantica[ PYTHON ]0.49 #09531149627/MonsterDeleter[ PYTHON ]0.41 #12vitali87/code-graph-rag[ PYTHON ]0.38 #13kaibush/grok-register[ PYTHON ]0.37

METRICS IN CONTEXT

MEDIAN ACROSS ALL 9726 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW

METRICVALUEMEDIANΔ MEDPERCENTILE

SCORE0.000.00-0.00ABOVE 27%

VELOCITY3.293.43-0.14ABOVE 47%

RETENTION47.6%33.3%+14.3 PPABOVE 70%

FORKS418130+288ABOVE 77%

SURPRISE0.000.01-0.01ABOVE 17%