ModelEngine-Group/nexent — GitHub trend

FINDING #3262 · UNIT ID 974157595

ModelEngine-Group/nexent

Nexent is a zero-code platform for auto-generating production-grade AI agents using Harness Engineering principles — unified tools, skills, memory, and orchestration with built-in constraints, feedback loops, and control planes.

[ PYTHON ][ ORG ][ GITHUB ↗ ]

SURPRISE SCORE

0.00

Score Breakdown

SURPRISE0.00503

ENGAGEMENT0.20

FRESHNESS1.42

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

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

10% OF STARS IN ARCHIVE

Growth Telemetry

VELOCITY /D

19.00

ACCEL

-0.11

RETENTION

60.6%

PEAK 2026-06-18 · FORK-RETENTION 0.0% · 570 STARS / WINDOW

Author Audience

AUDIENCE

3,740

FOLLOWERS

846

OWNER ★

10,238

Engagement Signals

FORKS

701

ISSUE AUTH

PR AUTH

UNIQUE STARGAZERS 570 / 570 (DIVERSITY 1.00)

Why This Is A Finding

ModelEngine-Group/nexent собрал 570 звёзд за окно, тогда как у автора всего 846 подписчиков — эффективная аудитория ≈ 3,740. Это даёт surprise-индекс 0.00503 (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 48% 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

SCORE0.000.00-0.00ABOVE 48%

VELOCITY19.004.23+14.77ABOVE 86%

RETENTION60.6%29.4%+31.2 PPABOVE 94%

FORKS70192+609ABOVE 89%

SURPRISE0.010.01-0.01ABOVE 31%