FINDING #856 · 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)
4% OF STARS IN ARCHIVE
Growth Telemetry
VELOCITY /D
8.00
ACCEL
-2.50
RETENTION
36.4%
PEAK 2026-08-09 · FORK-RETENTION 0.0% · 24 STARS / WINDOW
Author Audience
AUDIENCE
122
FOLLOWERS
55
OWNER ★
668
Engagement Signals
FORKS
41
ISSUE AUTH
0
PR AUTH
0
UNIQUE STARGAZERS 24 / 24 (DIVERSITY 1.00)
Why This Is A Finding
vshulcz/deja-vu собрал 24 звёзд за окно, тогда как у автора всего 55 подписчиков — эффективная аудитория ≈ 122. Это даёт surprise-индекс 0.0494 (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 90% OF 8676 FINDINGS
METRICS IN CONTEXT
MEDIAN ACROSS ALL 8676 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW
METRICVALUEMEDIANΔ MEDPERCENTILE
SCORE0.020.00+0.02ABOVE 90%
VELOCITY8.005.67+2.33ABOVE 63%
RETENTION36.4%33.3%+3.0 PPABOVE 52%
FORKS41339-298ABOVE 17%
SURPRISE0.050.00+0.05ABOVE 88%