Human-Agent-Society/CORAL — GitHub trend

FINDING #1209 · 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

SURPRISE0.0277

ENGAGEMENT0.20

FRESHNESS1.00

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

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

2% OF STARS IN ARCHIVE

Growth Telemetry

VELOCITY /D

6.67

ACCEL

-1.00

RETENTION

40.0%

PEAK 2026-07-14 · FORK-RETENTION 0.0% · 20 STARS / WINDOW

Author Audience

AUDIENCE

201

FOLLOWERS

OWNER ★

822

Engagement Signals

FORKS

105

ISSUE AUTH

PR AUTH

UNIQUE STARGAZERS 20 / 20 (DIVERSITY 1.00)

Why This Is A Finding

Human-Agent-Society/CORAL собрал 20 звёзд за окно, тогда как у автора всего 19 подписчиков — эффективная аудитория ≈ 201. Это даёт surprise-индекс 0.0277 (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 76% OF 5024 FINDINGS

#02Git-creat7/grokRegister-cpa[ PYTHON ]0.72 #09vinhhien112/Three.js-Object-Sculptor-Codex-Plugin[ PYTHON ]0.51 #10domanski-ai/headroom[ PYTHON ]0.50 #12William-Lu-stack/LuxyAI[ PYTHON ]0.46 #15fqscfqj/Y2A-Auto[ PYTHON ]0.37

METRICS IN CONTEXT

MEDIAN ACROSS ALL 5024 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW

METRICVALUEMEDIANΔ MEDPERCENTILE

SCORE0.010.00+0.01ABOVE 76%

VELOCITY6.676.670.00ABOVE 49%

RETENTION40.0%46.5%-6.5 PPABOVE 44%

FORKS105116-11ABOVE 47%

SURPRISE0.030.01+0.01ABOVE 68%