FINDING #78 · UNIT ID 1202290616
dirac-run/dirac
Coding Agent singularly focused efficiency and context curation. Reduces API costs by 50-80% vs other agent AND improves the code quality at the same time. Uses Hash Anchored edits, massively parallel operations, AST manipulation and many many other optimizations. https://dirac.run/
SURPRISE SCORE
0.00
Score Breakdown
SCORE = SURPRISE × ENGAGEMENT^0.7 × FRESHNESS × VISIBILITY × CONFIDENCE
SURPRISE = WINDOW STARS / DAYS / (AUDIENCE + FLOOR)
100% OF STARS IN ARCHIVE
Growth Telemetry
VELOCITY /D
7.80
ACCEL
+0.05
RETENTION
1.9%
PEAK 2026-04-27 · FORK-RETENTION 0.0% · 1,404 STARS / WINDOW
Author Audience
AUDIENCE
164
FOLLOWERS
24
OWNER ★
1,404
Engagement Signals
FORKS
82
ISSUE AUTH
0
PR AUTH
0
UNIQUE STARGAZERS 1,404 / 1,404 (DIVERSITY 1.00)
Why This Is A Finding
dirac-run/dirac собрал 1,404 звёзд за окно, тогда как у автора всего 24 подписчиков — эффективная аудитория ≈ 164. Это даёт surprise-индекс 0.0382 (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 99% OF 6727 FINDINGS
METRICS IN CONTEXT
MEDIAN ACROSS ALL 6727 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW
METRICVALUEMEDIANΔ MEDPERCENTILE
SCORE0.040.00+0.04ABOVE 99%
VELOCITY7.803.21+4.59ABOVE 78%
RETENTION1.9%10.8%-8.9 PPABOVE 6%
FORKS8295-13ABOVE 45%
SURPRISE0.040.01+0.03ABOVE 97%