NousResearch/hermes-agent-self-evolution — GitHub trend

◂ BACK TO LEADERBOARD

FINDING #8079 · UNIT ID 1176753219

NousResearch/hermes-agent-self-evolution

⚒ Evolutionary self-improvement for Hermes Agent — optimize skills, prompts, and code using DSPy + GEPA

[ PYTHON ][ ORG ][ GITHUB ↗ ]

SURPRISE SCORE

0.00

Score Breakdown

SURPRISE0.000184

ENGAGEMENT0.40

FRESHNESS1.00

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

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

2% OF STARS IN ARCHIVE

Growth Telemetry

VELOCITY /D

12.43

ACCEL

-1.07

RETENTION

63.9%

PEAK 2026-08-22 · FORK-RETENTION 81.8% · 87 STARS / WINDOW

Author Audience

AUDIENCE

67,422

FOLLOWERS

8,356

OWNER ★

253,947

Engagement Signals

FORKS

604

ISSUE AUTH

PR AUTH

UNIQUE STARGAZERS 87 / 87 (DIVERSITY 1.00)

Why This Is A Finding

NousResearch/hermes-agent-self-evolution собрал 87 звёзд за окно, тогда как у автора всего 8,356 подписчиков — эффективная аудитория ≈ 67,422. Это даёт surprise-индекс 0.000184 (звёзды относительно охвата автора, а не в абсолюте). Удержание форков 81.8% и 0 внешних контрибьюторов отделяют реальный инструмент от разовой вспышки. Акселерация отрицательная — внимание остывает после пика.

Related Findings

RANKS ABOVE 17% OF 9760 FINDINGS

#08MddIdd/mdd-sim-gateway[ PYTHON ]0.41 #17litaolemo/xtquant_big_convert[ PYTHON ]0.36 #20LBH-123-AI/Comfyui_Minimax_h3_latent_Upscaler[ PYTHON ]0.34 #24zeenie-ai/OpenCompany[ PYTHON ]0.30 #25917Dhj/DeepPaperNote[ PYTHON ]0.29

METRICS IN CONTEXT

MEDIAN ACROSS ALL 9760 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW

METRICVALUEMEDIANΔ MEDPERCENTILE

SCORE0.000.00-0.00ABOVE 17%

VELOCITY12.433.71+8.71ABOVE 82%

RETENTION63.9%38.0%+25.9 PPABOVE 84%

FORKS60486+518ABOVE 89%

SURPRISE0.000.01-0.01ABOVE 6%