vstorm-co/pydantic-deepagents — GitHub trend

FINDING #3611 · UNIT ID 1106580780

vstorm-co/pydantic-deepagents

Open-source, self-hosted Claude Code - a terminal AI assistant and the Python framework behind it. Tool-calling, sandboxed execution, multi-agent teams, skills, checkpoints, unlimited context - on Pydantic AI, any model.

[ PYTHON ][ ORG ][ VERIFIED ][ GITHUB ↗ ]

SURPRISE SCORE

0.00

Score Breakdown

SURPRISE0.0035

ENGAGEMENT0.20

FRESHNESS1.35

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

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

11% OF STARS IN ARCHIVE

Growth Telemetry

VELOCITY /D

3.67

ACCEL

-0.02

RETENTION

23.1%

PEAK 2026-07-02 · FORK-RETENTION 0.0% · 110 STARS / WINDOW

Author Audience

AUDIENCE

1,007

FOLLOWERS

141

OWNER ★

3,317

Engagement Signals

FORKS

113

ISSUE AUTH

PR AUTH

UNIQUE STARGAZERS 110 / 110 (DIVERSITY 1.00)

Why This Is A Finding

vstorm-co/pydantic-deepagents собрал 110 звёзд за окно, тогда как у автора всего 141 подписчиков — эффективная аудитория ≈ 1,007. Это даёт surprise-индекс 0.0035 (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 43% OF 6295 FINDINGS

#01shy3130/tickflow-stock-panel[ PYTHON ]0.46 #06Panniantong/Agent-Reach[ PYTHON ]0.29 #10sums001/Windows-Copilot-API[ PYTHON ]0.27 #12HUANGCHIHHUNGLeo/claude-real-video[ PYTHON ]0.24 #14realiti4/claude-swap[ PYTHON ]0.21

METRICS IN CONTEXT

MEDIAN ACROSS ALL 6295 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW

METRICVALUEMEDIANΔ MEDPERCENTILE

SCORE0.000.00-0.00ABOVE 43%

VELOCITY3.674.23-0.57ABOVE 44%

RETENTION23.1%29.4%-6.3 PPABOVE 37%

FORKS11392+21ABOVE 55%

SURPRISE0.000.01-0.01ABOVE 26%