FINDING #163 · UNIT ID 1300173275
vshulcz/deja-vu
Your agents already solved this. deja finds it — it indexes the sessions your coding agents already wrote to disk, months of history from before you installed it, and recalls them automatically at session start across seventeen harnesses. 84.9% hit@1 on LongMemEval-S, no LLM, no embeddings. One zero-dep binary, fully local.
SURPRISE SCORE
0.00
Score Breakdown
SCORE = SURPRISE × ENGAGEMENT^0.7 × FRESHNESS × VISIBILITY × CONFIDENCE
SURPRISE = WINDOW STARS / DAYS / (AUDIENCE + FLOOR)
9% OF STARS IN ARCHIVE
Growth Telemetry
VELOCITY /D
18.00
ACCEL
+21.50
RETENTION
0.0%
PEAK 2026-08-05 · FORK-RETENTION 0.0% · 54 STARS / WINDOW
Author Audience
AUDIENCE
118
FOLLOWERS
55
OWNER ★
630
Engagement Signals
FORKS
40
ISSUE AUTH
0
PR AUTH
0
UNIQUE STARGAZERS 54 / 54 (DIVERSITY 1.00)
Why This Is A Finding
vshulcz/deja-vu собрал 54 звёзд за окно, тогда как у автора всего 55 подписчиков — эффективная аудитория ≈ 118. Это даёт surprise-индекс 0.11 (звёзды относительно охвата автора, а не в абсолюте). Удержание форков 0.0% и 0 внешних контрибьюторов отделяют реальный инструмент от разовой вспышки. Акселерация положительная — рост ещё не выдохся.
Related Findings
RANKS ABOVE 98% OF 9486 FINDINGS
METRICS IN CONTEXT
MEDIAN ACROSS ALL 9486 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW
METRICVALUEMEDIANΔ MEDPERCENTILE
SCORE0.120.00+0.12ABOVE 98%
VELOCITY18.005.67+12.33ABOVE 83%
RETENTION0.0%43.5%-43.5 PPABOVE 0%
FORKS40358-318ABOVE 15%
SURPRISE0.110.00+0.11ABOVE 96%