FINDING #4988 · UNIT ID 926861272
dzhng/deep-research
An AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, web scraping, and large language models. The goal of this repo is to provide the simplest implementation of a deep research agent - e.g. an agent that can refine its research direction overtime and deep dive into a topic.
SURPRISE SCORE
0.00
Score Breakdown
SCORE = SURPRISE × ENGAGEMENT^0.7 × FRESHNESS × VISIBILITY × CONFIDENCE
SURPRISE = WINDOW STARS / DAYS / (AUDIENCE + FLOOR)
0% OF STARS IN ARCHIVE
Growth Telemetry
VELOCITY /D
7.00
ACCEL
-1.50
RETENTION
66.7%
PEAK 2026-10-20 · FORK-RETENTION 0.0% · 21 STARS / WINDOW
Author Audience
AUDIENCE
3,630
FOLLOWERS
979
OWNER ★
26,513
Engagement Signals
FORKS
2,008
ISSUE AUTH
0
PR AUTH
0
UNIQUE STARGAZERS 21 / 21 (DIVERSITY 1.00)
Why This Is A Finding
dzhng/deep-research собрал 21 звёзд за окно, тогда как у автора всего 979 подписчиков — эффективная аудитория ≈ 3,630. Это даёт surprise-индекс 0.00191 (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 45% OF 9064 FINDINGS
METRICS IN CONTEXT
MEDIAN ACROSS ALL 9064 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW
METRICVALUEMEDIANΔ MEDPERCENTILE
SCORE0.000.00-0.00ABOVE 45%
VELOCITY7.005.67+1.33ABOVE 56%
RETENTION66.7%30.0%+36.7 PPABOVE 83%
FORKS2,008328+1,680ABOVE 82%
SURPRISE0.000.01-0.00ABOVE 34%