ClaudioDrews/memory-os — GitHub trend

FINDING #1215 · UNIT ID 1255412388

ClaudioDrews/memory-os

A 7-layer memory operating system for Hermes Agent — persistent memory with Qdrant, structured facts, fabric recall, auto-curated wiki, and surgical context injection. Runs locally, any LLM provider.

[ PYTHON ][ GITHUB ↗ ]

SURPRISE SCORE

0.00

Score Breakdown

SURPRISE0.0243

ENGAGEMENT0.20

FRESHNESS1.34

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

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

12% OF STARS IN ARCHIVE

Growth Telemetry

VELOCITY /D

5.27

ACCEL

-0.21

RETENTION

18.8%

PEAK 2026-06-17 · FORK-RETENTION 0.0% · 158 STARS / WINDOW

Author Audience

AUDIENCE

177

FOLLOWERS

OWNER ★

1,279

Engagement Signals

FORKS

119

ISSUE AUTH

PR AUTH

UNIQUE STARGAZERS 158 / 158 (DIVERSITY 1.00)

Why This Is A Finding

ClaudioDrews/memory-os собрал 158 звёзд за окно, тогда как у автора всего 49 подписчиков — эффективная аудитория ≈ 177. Это даёт surprise-индекс 0.0243 (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 81% 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 81%

VELOCITY5.274.23+1.03ABOVE 58%

RETENTION18.8%29.4%-10.7 PPABOVE 29%

FORKS11992+27ABOVE 57%

SURPRISE0.020.01+0.01ABOVE 70%