FINDING #5973 · UNIT ID 1129311820
neo4j-labs/agent-memory
A graph-native memory system for AI agents and context graphs. Store conversations, build knowledge graphs, and let your agents learn from their own reasoning — all backed by Neo4j.
SURPRISE SCORE
0.00
Score Breakdown
SCORE = SURPRISE × ENGAGEMENT^0.7 × FRESHNESS × VISIBILITY × CONFIDENCE
SURPRISE = WINDOW STARS / DAYS / (AUDIENCE + FLOOR)
61% OF STARS IN ARCHIVE
[BOT] SUSPECTED STAR BOT — SCORE PENALIZED. SIGNATURES:
S2 · NO EXTERNAL ISSUE/PR AUTHORS DESPITE 100+ STARS
S5 · PREDATES WINDOW, YET HALF+ OF ALL ITS STARS LANDED IN IT
Growth Telemetry
VELOCITY /D
2.52
ACCEL
-0.02
RETENTION
11.9%
PEAK 2026-05-18 · FORK-RETENTION 0.0% · 227 STARS / WINDOW
Author Audience
AUDIENCE
2,920
FOLLOWERS
332
OWNER ★
9,114
Engagement Signals
FORKS
85
ISSUE AUTH
0
PR AUTH
0
UNIQUE STARGAZERS 227 / 227 (DIVERSITY 1.00)
Why This Is A Finding
neo4j-labs/agent-memory собрал 227 звёзд за окно, тогда как у автора всего 332 подписчиков — эффективная аудитория ≈ 2,920. Это даёт surprise-индекс 0.000852 (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 6% OF 6380 FINDINGS
METRICS IN CONTEXT
MEDIAN ACROSS ALL 6380 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW
METRICVALUEMEDIANΔ MEDPERCENTILE
SCORE0.000.00-0.00ABOVE 6%
VELOCITY2.523.99-1.47ABOVE 30%
RETENTION11.9%17.1%-5.2 PPABOVE 36%
FORKS8590-4ABOVE 48%
SURPRISE0.000.01-0.01ABOVE 13%