datawhalechina/deepagents-in-action — GitHub trend

◂ BACK TO LEADERBOARD

FINDING #8872 · UNIT ID 1229618308

datawhalechina/deepagents-in-action

📚 《Deep Agents 实战》—— LangChain 官方大使出品，基于 LangChain / LangGraph 生态，从零构建生产级 AI Agent 的完整指南

[ JUPYTER NOTEBOOK ][ ORG ][ GITHUB ↗ ]

SURPRISE SCORE

0.00

Score Breakdown

SURPRISE0.0000543

ENGAGEMENT0.43

FRESHNESS1.27

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

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

9% OF STARS IN ARCHIVE

Growth Telemetry

VELOCITY /D

8.10

ACCEL

-0.18

RETENTION

16.4%

PEAK 2026-10-08 · FORK-RETENTION 28.6% · 243 STARS / WINDOW

Author Audience

AUDIENCE

149,198

FOLLOWERS

34,182

OWNER ★

404,172

Engagement Signals

FORKS

289

ISSUE AUTH

PR AUTH

UNIQUE STARGAZERS 243 / 243 (DIVERSITY 1.00)

Why This Is A Finding

datawhalechina/deepagents-in-action собрал 243 звёзд за окно, тогда как у автора всего 34,182 подписчиков — эффективная аудитория ≈ 149,198. Это даёт surprise-индекс 0.0000543 (звёзды относительно охвата автора, а не в абсолюте). Удержание форков 28.6% и 0 внешних контрибьюторов отделяют реальный инструмент от разовой вспышки. Акселерация отрицательная — внимание остывает после пика.

Related Findings

RANKS ABOVE 8% OF 9675 FINDINGS

#260Akun-python/autumn-recruitment[ JUPYTER NOTEBOOK ]0.0653 #414Liuziyu77/Valen[ JUPYTER NOTEBOOK ]0.0361 #969philshiu/Drosophila_brain_model[ JUPYTER NOTEBOOK ]0.0219 #994bicky007/100-python-projects[ JUPYTER NOTEBOOK ]0.0216 #1062PaulamiB-git/solutions-prototypes[ JUPYTER NOTEBOOK ]0.0204

METRICS IN CONTEXT

MEDIAN ACROSS ALL 9675 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW

METRICVALUEMEDIANΔ MEDPERCENTILE

SCORE0.000.00-0.00ABOVE 8%

VELOCITY8.103.80+4.30ABOVE 73%

RETENTION16.4%20.3%-3.9 PPABOVE 41%

FORKS289138+151ABOVE 67%

SURPRISE0.000.01-0.01ABOVE 4%