SamurAIGPT/llm-wiki-agent — GitHub trend

FINDING #6419 · UNIT ID 630824392

SamurAIGPT/llm-wiki-agent

A personal knowledge base that builds and maintains itself. Drop in sources — Claude (or Codex/Gemini) reads them, extracts knowledge, and maintains a persistent interlinked wiki. Works with Claude Code, Codex, OpenCode, Gemini CLI. No API key needed.

[ PYTHON ][ ORG ][ GITHUB ↗ ]

SURPRISE SCORE

0.00

Score Breakdown

SURPRISE0.00145

ENGAGEMENT0.36

FRESHNESS1.24

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

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

5% OF STARS IN ARCHIVE

Growth Telemetry

VELOCITY /D

5.47

ACCEL

+0.12

RETENTION

28.6%

PEAK 2026-08-22 · FORK-RETENTION 18.8% · 164 STARS / WINDOW

Author Audience

AUDIENCE

3,728

FOLLOWERS

605

OWNER ★

12,588

Engagement Signals

FORKS

399

ISSUE AUTH

PR AUTH

UNIQUE STARGAZERS 164 / 164 (DIVERSITY 1.00)

Why This Is A Finding

SamurAIGPT/llm-wiki-agent собрал 164 звёзд за окно, тогда как у автора всего 605 подписчиков — эффективная аудитория ≈ 3,728. Это даёт surprise-индекс 0.00145 (звёзды относительно охвата автора, а не в абсолюте). Удержание форков 18.8% и 0 внешних контрибьюторов отделяют реальный инструмент от разовой вспышки. Акселерация положительная — рост ещё не выдохся.

Related Findings

RANKS ABOVE 33% OF 9595 FINDINGS

#02guillaumemeyer/watermarks-remover[ PYTHON ]0.43 #09awesome-dsh-plugin/awesome-dsh-plugin[ PYTHON ]0.38 #10wang2122/sprix-sage-router[ PYTHON ]0.37 #16virgiliojr94/book-to-skill[ PYTHON ]0.31 #19ayghri/i-have-adhd[ PYTHON ]0.28

METRICS IN CONTEXT

MEDIAN ACROSS ALL 9595 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW

METRICVALUEMEDIANΔ MEDPERCENTILE

SCORE0.000.00-0.00ABOVE 33%

VELOCITY5.473.67+1.80ABOVE 64%

RETENTION28.6%24.6%+3.9 PPABOVE 58%

FORKS399115+284ABOVE 79%

SURPRISE0.000.01-0.01ABOVE 18%