air-embodied-brain/Zetta-Embodiment — GitHub trend

FINDING #189 · UNIT ID 1337915408

air-embodied-brain/Zetta-Embodiment

Zetta is an efficient closed-loop embodied harness for self-evolving physical intelligence. It evolves code-based runtime critics and recovery skills online while keeping the base policy frozen. Project Page: https://air-embodied-brain.github.io/zetta/

[ PYTHON ][ ORG ][ GITHUB ↗ ]

SURPRISE SCORE

0.00

Score Breakdown

SURPRISE0.0579

ENGAGEMENT0.81

FRESHNESS1.71

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

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

74% OF STARS IN ARCHIVE

Growth Telemetry

VELOCITY /D

13.70

ACCEL

+1.77

RETENTION

67.6%

PEAK 2026-08-20 · FORK-RETENTION 96.4% · 411 STARS / WINDOW

Author Audience

AUDIENCE

197

FOLLOWERS

OWNER ★

633

Engagement Signals

FORKS

ISSUE AUTH

PR AUTH

UNIQUE STARGAZERS 411 / 411 (DIVERSITY 1.00)

Why This Is A Finding

air-embodied-brain/Zetta-Embodiment собрал 411 звёзд за окно, тогда как у автора всего 35 подписчиков — эффективная аудитория ≈ 197. Это даёт surprise-индекс 0.0579 (звёзды относительно охвата автора, а не в абсолюте). Удержание форков 96.4% и 0 внешних контрибьюторов отделяют реальный инструмент от разовой вспышки. Акселерация положительная — рост ещё не выдохся.

Related Findings

RANKS ABOVE 98% OF 9595 FINDINGS

#02guillaumemeyer/watermarks-remover[ PYTHON ]0.43 #09awesome-dsh-plugin/awesome-dsh-plugin[ PYTHON ]0.38 #10wang2122/sprix-sage-router[ PYTHON ]0.37 #16virgiliojr94/book-to-skill[ PYTHON ]0.31 #19ayghri/i-have-adhd[ PYTHON ]0.28

METRICS IN CONTEXT

MEDIAN ACROSS ALL 9595 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW

METRICVALUEMEDIANΔ MEDPERCENTILE

SCORE0.090.00+0.08ABOVE 98%

VELOCITY13.703.67+10.03ABOVE 85%

RETENTION67.6%24.6%+43.0 PPABOVE 98%

FORKS39115-76ABOVE 25%

SURPRISE0.060.01+0.05ABOVE 93%