LearningCircuit/local-deep-research — GitHub trend

FINDING #573 · 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

SURPRISE0.00273

ENGAGEMENT1.11

FRESHNESS1.06

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

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

6% OF STARS IN ARCHIVE

Growth Telemetry

VELOCITY /D

2.91

ACCEL

-0.00

RETENTION

3.2%

PEAK 2026-05-09 · FORK-RETENTION 23.7% · 523 STARS / WINDOW

Author Audience

AUDIENCE

1,026

FOLLOWERS

145

OWNER ★

8,805

Engagement Signals

FORKS

775

ISSUE AUTH

PR AUTH

315

UNIQUE STARGAZERS 522 / 523 (DIVERSITY 1.00)

Why This Is A Finding

LearningCircuit/local-deep-research собрал 523 звёзд за окно, тогда как у автора всего 145 подписчиков — эффективная аудитория ≈ 1,026. Это даёт surprise-индекс 0.00273 (звёзды относительно охвата автора, а не в абсолюте). Удержание форков 23.7% и 373 внешних контрибьюторов отделяют реальный инструмент от разовой вспышки. Акселерация отрицательная — внимание остывает после пика.

Related Findings

RANKS ABOVE 78% OF 2559 FINDINGS

#02databricks-solutions/ai-dev-kit[ PYTHON ]0.10 #09sickn33/agentic-awesome-skills[ PYTHON ]0.019 #10cft0808/edict[ PYTHON ]0.0183 #16ZhuLinsen/daily_stock_analysis[ PYTHON ]0.0159 #24jundot/omlx[ PYTHON ]0.014

METRICS IN CONTEXT

MEDIAN ACROSS ALL 2559 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW

METRICVALUEMEDIANΔ MEDPERCENTILE

SCORE0.000.00+0.00ABOVE 78%

VELOCITY2.912.88+0.02ABOVE 50%

RETENTION3.2%6.3%-3.1 PPABOVE 26%

FORKS7751,183-408ABOVE 40%

SURPRISE0.000.00+0.00ABOVE 75%