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

FINDING #81 · 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

SURPRISE0.17

ENGAGEMENT1.12

FRESHNESS1.00

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

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

49% OF STARS IN ARCHIVE

Growth Telemetry

VELOCITY /D

39.29

ACCEL

-1.75

RETENTION

74.5%

PEAK 2026-08-24 · FORK-RETENTION 65.0% · 275 STARS / WINDOW

Author Audience

AUDIENCE

197

FOLLOWERS

OWNER ★

633

Engagement Signals

FORKS

ISSUE AUTH

PR AUTH

UNIQUE STARGAZERS 275 / 275 (DIVERSITY 1.00)

Why This Is A Finding

air-embodied-brain/Zetta-Embodiment собрал 275 звёзд за окно, тогда как у автора всего 35 подписчиков — эффективная аудитория ≈ 197. Это даёт surprise-индекс 0.17 (звёзды относительно охвата автора, а не в абсолюте). Удержание форков 65.0% и 0 внешних контрибьюторов отделяют реальный инструмент от разовой вспышки. Акселерация отрицательная — внимание остывает после пика.

Related Findings

RANKS ABOVE 99% OF 9771 FINDINGS

#05MddIdd/mdd-sim-gateway[ PYTHON ]0.41 #08zeenie-ai/OpenCompany[ PYTHON ]0.38 #15litaolemo/xtquant_big_convert[ PYTHON ]0.33 #23917Dhj/DeepPaperNote[ PYTHON ]0.27 #24LBH-123-AI/Comfyui_Minimax_h3_latent_Upscaler[ PYTHON ]0.27

METRICS IN CONTEXT

MEDIAN ACROSS ALL 9771 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW

METRICVALUEMEDIANΔ MEDPERCENTILE

SCORE0.180.00+0.18ABOVE 99%

VELOCITY39.293.71+35.57ABOVE 94%

RETENTION74.5%39.3%+35.2 PPABOVE 93%

FORKS3991-52ABOVE 30%

SURPRISE0.170.01+0.16ABOVE 98%