▲РЕПО НЕТ В ОКНЕ 3D. ПОКАЗАН FINDING ИЗ ОКНА 180D (180 days) — РАНГ #2228.
FINDING #2228 · UNIT ID 1197656406
open-multi-agent/open-multi-agent
TypeScript AI agent orchestration framework with dynamic workflows. Describe the goal, not the graph: a coordinator plans the task DAG at runtime and runs it on any LLM (Claude, ChatGPT, Gemini, DeepSeek, or local models).
SURPRISE SCORE
0.00
Score Breakdown
SCORE = SURPRISE × ENGAGEMENT^0.7 × FRESHNESS × VISIBILITY × CONFIDENCE
SURPRISE = WINDOW STARS / DAYS / (AUDIENCE + FLOOR)
19% OF STARS IN ARCHIVE
[BOT] SUSPECTED STAR BOT — SCORE PENALIZED. SIGNATURES:
S1b · REPO PREDATES ITS OWNER ACCOUNT (TRANSFERRED / RE-CREATED)
S7 · THIS REPO IS ~ALL OF THE OWNER'S STARS
S11 · ONE ACCOUNT GENERATES MOST OF THE "COMMUNITY" ACTIVITY
Growth Telemetry
VELOCITY /D
6.88
ACCEL
-0.06
RETENTION
0.9%
PEAK 2026-04-05 · FORK-RETENTION 16.7% · 1,238 STARS / WINDOW
Author Audience
AUDIENCE
1,352
FOLLOWERS
9
OWNER ★
6,672
Engagement Signals
FORKS
2,414
ISSUE AUTH
24
PR AUTH
38
UNIQUE STARGAZERS 1,237 / 1,238 (DIVERSITY 1.00)
Why This Is A Finding
open-multi-agent/open-multi-agent собрал 1,238 звёзд за окно, тогда как у автора всего 9 подписчиков — эффективная аудитория ≈ 1,352. Это даёт surprise-индекс 0.00494 (звёзды относительно охвата автора, а не в абсолюте). Удержание форков 16.7% и 62 внешних контрибьюторов отделяют реальный инструмент от разовой вспышки. Акселерация отрицательная — внимание остывает после пика.
Related Findings
RANKS ABOVE 13% OF 2559 FINDINGS
METRICS IN CONTEXT
MEDIAN ACROSS ALL 2559 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW
METRICVALUEMEDIANΔ MEDPERCENTILE
SCORE0.000.00-0.00ABOVE 13%
VELOCITY6.882.88+3.99ABOVE 82%
RETENTION0.9%6.3%-5.4 PPABOVE 2%
FORKS2,4141,183+1,231ABOVE 68%
SURPRISE0.000.00+0.00ABOVE 90%