LearningCircuit/local-deep-research — GitHub trend

FINDING #4333 · UNIT ID 929868765

LearningCircuit/local-deep-research

~95% on SimpleQA (e.g. Qwen3.6-27B on a 3090). Supports all local and cloud LLMs (llama.cpp, Ollama, Google, ...). 10+ search engines - arXiv, PubMed, your private documents. Everything Local & Encrypted.

[ PYTHON ][ GITHUB ↗ ]

SURPRISE SCORE

0.00

Score Breakdown

SURPRISE0.00539

ENGAGEMENT0.35

FRESHNESS1.41

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

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

2% OF STARS IN ARCHIVE

Growth Telemetry

VELOCITY /D

5.90

ACCEL

-0.02

RETENTION

33.6%

PEAK 2026-08-09 · FORK-RETENTION 52.9% · 177 STARS / WINDOW

Author Audience

AUDIENCE

1,055

FOLLOWERS

152

OWNER ★

9,026

Engagement Signals

FORKS

797

ISSUE AUTH

PR AUTH

UNIQUE STARGAZERS 177 / 177 (DIVERSITY 1.00)

Why This Is A Finding

LearningCircuit/local-deep-research собрал 177 звёзд за окно, тогда как у автора всего 152 подписчиков — эффективная аудитория ≈ 1,055. Это даёт surprise-индекс 0.00539 (звёзды относительно охвата автора, а не в абсолюте). Удержание форков 52.9% и 0 внешних контрибьюторов отделяют реальный инструмент от разовой вспышки. Акселерация отрицательная — внимание остывает после пика.

Related Findings

RANKS ABOVE 55% OF 9591 FINDINGS

#02guillaumemeyer/watermarks-remover[ PYTHON ]0.42 #09awesome-dsh-plugin/awesome-dsh-plugin[ PYTHON ]0.38 #11wang2122/sprix-sage-router[ PYTHON ]0.36 #16virgiliojr94/book-to-skill[ PYTHON ]0.31 #19ayghri/i-have-adhd[ PYTHON ]0.29

METRICS IN CONTEXT

MEDIAN ACROSS ALL 9591 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW

METRICVALUEMEDIANΔ MEDPERCENTILE

SCORE0.000.00+0.00ABOVE 55%

VELOCITY5.903.63+2.27ABOVE 66%

RETENTION33.6%24.8%+8.7 PPABOVE 67%

FORKS797120+677ABOVE 88%

SURPRISE0.010.01-0.00ABOVE 40%