Human-Agent-Society/CORAL — GitHub trend

FINDING #2244 · UNIT ID 1183057754

Human-Agent-Society/CORAL

🔥🔥COLM 2026🔥🔥 CORAL is a robust, lightweight infrastructure for multi-agent autonomous self-evolution, built for autoresearch. Works with Claude Code, Codex, Cursor, OpenCode, Kiro, and more.

[ PYTHON ][ ORG ][ GITHUB ↗ ]

SURPRISE SCORE

0.00

Score Breakdown

SURPRISE0.012

ENGAGEMENT0.20

FRESHNESS1.38

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

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

11% OF STARS IN ARCHIVE

Growth Telemetry

VELOCITY /D

2.90

ACCEL

+0.06

RETENTION

40.0%

PEAK 2026-07-14 · FORK-RETENTION 0.0% · 87 STARS / WINDOW

Author Audience

AUDIENCE

202

FOLLOWERS

OWNER ★

822

Engagement Signals

FORKS

105

ISSUE AUTH

PR AUTH

UNIQUE STARGAZERS 87 / 87 (DIVERSITY 1.00)

Why This Is A Finding

Human-Agent-Society/CORAL собрал 87 звёзд за окно, тогда как у автора всего 19 подписчиков — эффективная аудитория ≈ 202. Это даёт surprise-индекс 0.012 (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 64% 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+0.00ABOVE 64%

VELOCITY2.904.23-1.33ABOVE 35%

RETENTION40.0%29.4%+10.6 PPABOVE 70%

FORKS10592+13ABOVE 53%

SURPRISE0.010.01-0.00ABOVE 50%