FINDING #747 · UNIT ID 1253654878
zhnt/loushang
AI-native agent harness for coding workflows by python: multi-model LLM orchestration, stateful sessions, tool governance, traceable delivery, and provider routing for GPT, Claude, DeepSeek, Qwen, Kimi, GLM, and MiniMax.
SURPRISE SCORE
0.00
Score Breakdown
SCORE = SURPRISE × ENGAGEMENT^0.7 × FRESHNESS × VISIBILITY × CONFIDENCE
SURPRISE = WINDOW STARS / DAYS / (AUDIENCE + FLOOR)
73% OF STARS IN ARCHIVE
[BOT] SUSPECTED STAR BOT — SCORE PENALIZED. SIGNATURES:
S2 · NO EXTERNAL ISSUE/PR AUTHORS DESPITE 100+ STARS
S5 · PREDATES WINDOW, YET HALF+ OF ALL ITS STARS LANDED IN IT
S7 · THIS REPO IS ~ALL OF THE OWNER'S STARS
Growth Telemetry
VELOCITY /D
16.13
ACCEL
+0.08
RETENTION
68.5%
PEAK 2026-07-10 · FORK-RETENTION 0.0% · 484 STARS / WINDOW
Author Audience
AUDIENCE
160
FOLLOWERS
93
OWNER ★
668
Engagement Signals
FORKS
121
ISSUE AUTH
0
PR AUTH
0
UNIQUE STARGAZERS 484 / 484 (DIVERSITY 1.00)
Why This Is A Finding
zhnt/loushang собрал 484 звёзд за окно, тогда как у автора всего 93 подписчиков — эффективная аудитория ≈ 160. Это даёт surprise-индекс 0.0807 (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 26% OF 1013 FINDINGS
METRICS IN CONTEXT
MEDIAN ACROSS ALL 1013 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW
METRICVALUEMEDIANΔ MEDPERCENTILE
SCORE0.000.00-0.00ABOVE 26%
VELOCITY16.137.20+8.93ABOVE 66%
RETENTION68.5%30.8%+37.7 PPABOVE 94%
FORKS12156+65ABOVE 63%
SURPRISE0.080.03+0.05ABOVE 79%