patchy631/ai-engineering-hub — GitHub trend

◂ BACK TO LEADERBOARD

▲РЕПО НЕТ В ОКНЕ 1D. ПОКАЗАН FINDING ИЗ ОКНА 90D (90 days) — РАНГ #585.

FINDING #585 · UNIT ID 876064934

patchy631/ai-engineering-hub

In-depth tutorials on LLMs, RAGs and real-world AI agent applications.

[ JUPYTER NOTEBOOK ][ GITHUB ↗ ]

SURPRISE SCORE

0.00

Score Breakdown

SURPRISE0.000241

ENGAGEMENT0.47

FRESHNESS1.20

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

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

0% OF STARS IN ARCHIVE

Growth Telemetry

VELOCITY /D

1.70

ACCEL

-0.06

RETENTION

9.4%

PEAK 2026-05-10 · FORK-RETENTION 50.0% · 153 STARS / WINDOW

Author Audience

AUDIENCE

7,016

FOLLOWERS

3,138

OWNER ★

38,779

Engagement Signals

FORKS

6,081

ISSUE AUTH

PR AUTH

UNIQUE STARGAZERS 153 / 153 (DIVERSITY 1.00)

Why This Is A Finding

patchy631/ai-engineering-hub собрал 153 звёзд за окно, тогда как у автора всего 3,138 подписчиков — эффективная аудитория ≈ 7,016. Это даёт surprise-индекс 0.000241 (звёзды относительно охвата автора, а не в абсолюте). Удержание форков 50.0% и 3 внешних контрибьюторов отделяют реальный инструмент от разовой вспышки. Акселерация отрицательная — внимание остывает после пика.

Related Findings

RANKS ABOVE 34% OF 891 FINDINGS

#141raiyanyahya/how-to-train-your-gpt[ JUPYTER NOTEBOOK ]0.00367 #282oracle-devrel/oracle-ai-developer-hub[ JUPYTER NOTEBOOK ]0.00135 #306Lordog/dive-into-llms[ JUPYTER NOTEBOOK ]0.000899 #335lyogavin/airllm[ JUPYTER NOTEBOOK ]0.000754 #537HandsOnLLM/Hands-On-Large-Language-Models[ JUPYTER NOTEBOOK ]0.000242

METRICS IN CONTEXT

MEDIAN ACROSS ALL 891 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW

METRICVALUEMEDIANΔ MEDPERCENTILE

SCORE0.000.00-0.00ABOVE 34%

VELOCITY1.702.86-1.16ABOVE 12%

RETENTION9.4%7.6%+1.8 PPABOVE 60%

FORKS6,0812,034+4,047ABOVE 77%

SURPRISE0.000.00-0.00ABOVE 37%