SamurAIGPT/llm-wiki-agent — GitHub trend

FINDING #6608 · 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

SURPRISE0.00175

ENGAGEMENT0.30

FRESHNESS1.00

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

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

1% OF STARS IN ARCHIVE

Growth Telemetry

VELOCITY /D

6.57

ACCEL

-1.57

RETENTION

31.3%

PEAK 2026-08-23 · FORK-RETENTION 0.0% · 46 STARS / WINDOW

Author Audience

AUDIENCE

3,724

FOLLOWERS

605

OWNER ★

12,588

Engagement Signals

FORKS

399

ISSUE AUTH

PR AUTH

UNIQUE STARGAZERS 46 / 46 (DIVERSITY 1.00)

Why This Is A Finding

SamurAIGPT/llm-wiki-agent собрал 46 звёзд за окно, тогда как у автора всего 605 подписчиков — эффективная аудитория ≈ 3,724. Это даёт surprise-индекс 0.00175 (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 32% OF 9771 FINDINGS

#05MddIdd/mdd-sim-gateway[ PYTHON ]0.41 #08zeenie-ai/OpenCompany[ PYTHON ]0.38 #15litaolemo/xtquant_big_convert[ PYTHON ]0.33 #23917Dhj/DeepPaperNote[ PYTHON ]0.27 #24LBH-123-AI/Comfyui_Minimax_h3_latent_Upscaler[ PYTHON ]0.27

METRICS IN CONTEXT

MEDIAN ACROSS ALL 9771 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW

METRICVALUEMEDIANΔ MEDPERCENTILE

SCORE0.000.00-0.00ABOVE 32%

VELOCITY6.573.71+2.86ABOVE 68%

RETENTION31.3%39.3%-8.1 PPABOVE 38%

FORKS39991+308ABOVE 83%

SURPRISE0.000.01-0.01ABOVE 19%