LearningCircuit/local-deep-research — GitHub trend

FINDING #3657 · 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

SURPRISE0.00457

ENGAGEMENT0.52

FRESHNESS1.00

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

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

0% OF STARS IN ARCHIVE

Growth Telemetry

VELOCITY /D

5.00

ACCEL

-1.50

RETENTION

75.0%

PEAK 2026-08-26 · FORK-RETENTION 0.0% · 15 STARS / WINDOW

Author Audience

AUDIENCE

1,054

FOLLOWERS

152

OWNER ★

9,026

Engagement Signals

FORKS

797

ISSUE AUTH

PR AUTH

UNIQUE STARGAZERS 15 / 15 (DIVERSITY 1.00)

Why This Is A Finding

LearningCircuit/local-deep-research собрал 15 звёзд за окно, тогда как у автора всего 152 подписчиков — эффективная аудитория ≈ 1,054. Это даёт surprise-индекс 0.00457 (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 62% OF 9558 FINDINGS

#03wang2122/sprix-sage-router[ PYTHON ]0.80 #04zeenie-ai/OpenCompany[ PYTHON ]0.78 #20HRuiCcc/music-geshizhuanhuan[ PYTHON ]0.41 #22MerZlin/dsh-pet-indesktop[ PYTHON ]0.39 #24handsomejustin/easy_tdx[ PYTHON ]0.38

METRICS IN CONTEXT

MEDIAN ACROSS ALL 9558 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW

METRICVALUEMEDIANΔ MEDPERCENTILE

SCORE0.000.00+0.00ABOVE 62%

VELOCITY5.005.67-0.67ABOVE 43%

RETENTION75.0%42.9%+32.1 PPABOVE 80%

FORKS797333+464ABOVE 67%

SURPRISE0.000.00+0.00ABOVE 51%