ed-donner/llm_engineering — GitHub trend

◂ BACK TO LEADERBOARD

FINDING #5195 · UNIT ID 850490697

ed-donner/llm_engineering

Repo to accompany my mastering LLM engineering course

[ JUPYTER NOTEBOOK ][ GITHUB ↗ ]

SURPRISE SCORE

0.00

Score Breakdown

SURPRISE0.00238

ENGAGEMENT0.81

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

14.57

ACCEL

+4.07

RETENTION

21.1%

PEAK 2026-08-28 · FORK-RETENTION 9.9% · 102 STARS / WINDOW

Author Audience

AUDIENCE

6,093

FOLLOWERS

4,591

OWNER ★

15,022

Engagement Signals

FORKS

7,040

ISSUE AUTH

PR AUTH

UNIQUE STARGAZERS 102 / 102 (DIVERSITY 1.00)

Why This Is A Finding

ed-donner/llm_engineering собрал 102 звёзд за окно, тогда как у автора всего 4,591 подписчиков — эффективная аудитория ≈ 6,093. Это даёт surprise-индекс 0.00238 (звёзды относительно охвата автора, а не в абсолюте). Удержание форков 9.9% и 0 внешних контрибьюторов отделяют реальный инструмент от разовой вспышки. Акселерация положительная — рост ещё не выдохся.

Related Findings

RANKS ABOVE 47% OF 9771 FINDINGS

#160gmonce/scikit-learn-book[ JUPYTER NOTEBOOK ]0.11 #246Nicolepcx/ai-agents-the-definitive-guide[ JUPYTER NOTEBOOK ]0.0638 #267xbsheng/atguigu-note[ JUPYTER NOTEBOOK ]0.0539 #293zorost/AI-Engineering-Lab[ JUPYTER NOTEBOOK ]0.0457 #304VintaBytes/Ciencia-de-datos[ JUPYTER NOTEBOOK ]0.0442

METRICS IN CONTEXT

MEDIAN ACROSS ALL 9771 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW

METRICVALUEMEDIANΔ MEDPERCENTILE

SCORE0.000.00-0.00ABOVE 47%

VELOCITY14.573.71+10.86ABOVE 85%

RETENTION21.1%39.3%-18.3 PPABOVE 26%

FORKS7,04091+6,949ABOVE 99%

SURPRISE0.000.01-0.01ABOVE 22%