langchain-ai/agents-from-scratch — GitHub trend

◂ BACK TO LEADERBOARD

FINDING #8965 · UNIT ID 958189434

langchain-ai/agents-from-scratch

Build an email assistant with human-in-the-loop and memory

[ JUPYTER NOTEBOOK ][ ORG ][ GITHUB ↗ ]

SURPRISE SCORE

0.00

Score Breakdown

SURPRISE0.0000192

ENGAGEMENT0.60

FRESHNESS1.00

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

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

1% OF STARS IN ARCHIVE

Growth Telemetry

VELOCITY /D

2.29

ACCEL

-0.29

RETENTION

25.0%

PEAK 2026-08-26 · FORK-RETENTION 0.0% · 16 STARS / WINDOW

Author Audience

AUDIENCE

119,242

FOLLOWERS

22,034

OWNER ★

376,030

Engagement Signals

FORKS

424

ISSUE AUTH

PR AUTH

UNIQUE STARGAZERS 16 / 16 (DIVERSITY 1.00)

Why This Is A Finding

langchain-ai/agents-from-scratch собрал 16 звёзд за окно, тогда как у автора всего 22,034 подписчиков — эффективная аудитория ≈ 119,242. Это даёт surprise-индекс 0.0000192 (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 8% OF 9755 FINDINGS

#249Nicolepcx/ai-agents-the-definitive-guide[ JUPYTER NOTEBOOK ]0.0676 #252gmonce/scikit-learn-book[ JUPYTER NOTEBOOK ]0.066 #291xbsheng/atguigu-note[ JUPYTER NOTEBOOK ]0.047 #409gothmania/pytutor[ JUPYTER NOTEBOOK ]0.0381 #433raiyanyahya/how-to-train-your-gpt[ JUPYTER NOTEBOOK ]0.0362

METRICS IN CONTEXT

MEDIAN ACROSS ALL 9755 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW

METRICVALUEMEDIANΔ MEDPERCENTILE

SCORE0.000.00-0.00ABOVE 8%

VELOCITY2.293.71-1.43ABOVE 28%

RETENTION25.0%37.5%-12.5 PPABOVE 31%

FORKS42490+334ABOVE 84%

SURPRISE0.000.01-0.01ABOVE 2%