Human-Agent-Society/CORAL — GitHub trend

FINDING #4106 · UNIT ID 1183057754

Human-Agent-Society/CORAL

Open-source autoresearch powered by autonomous coding agents. Run Claude Code, OpenCode, and Codex with grading, shared knowledge, and multi-agent evolution. Accepted at COLM 2026.

[ PYTHON ][ ORG ][ GITHUB ↗ ]

SURPRISE SCORE

0.00

Score Breakdown

SURPRISE0.0116

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

3.14

ACCEL

+0.14

RETENTION

41.7%

PEAK 2026-08-27 · FORK-RETENTION 0.0% · 22 STARS / WINDOW

Author Audience

AUDIENCE

230

FOLLOWERS

OWNER ★

940

Engagement Signals

FORKS

119

ISSUE AUTH

PR AUTH

UNIQUE STARGAZERS 22 / 22 (DIVERSITY 1.00)

Why This Is A Finding

Human-Agent-Society/CORAL собрал 22 звёзд за окно, тогда как у автора всего 21 подписчиков — эффективная аудитория ≈ 230. Это даёт surprise-индекс 0.0116 (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 58% 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

SCORE0.000.00+0.00ABOVE 58%

VELOCITY3.143.71-0.57ABOVE 43%

RETENTION41.7%39.3%+2.3 PPABOVE 53%

FORKS11991+28ABOVE 56%

SURPRISE0.010.01+0.00ABOVE 56%