adk-memory-self-improvement

SKILLFlujo de trabajocomunidad
v0.0.0Folken2MITActualizado hace 15 dFuente →

EXPERIMENTAL, opt-in memory self-improvement for long-lived ADK agents — relevance-conditioned preload, the periodic consolidation "dream" pass, the after-turn judge fork, fire-and-forget sibling runs, per-session throttling, and the skill curator that proposes SKILL.md files. Read before enabling a

Community-submitted skill. Not yet reviewed by the Forge team. Full prompt content may not be available.Request review →
2Estrellas del repo
1Clientes
1Formatos
hace 15 dÚltima actualización
Skill
AutorFolken2
Versión0.0.0
LicenciaMIT
CategoríaFlujo de trabajo
Formatosskill.md
PromptNo publicado
Compatibilidad
Claude✓ Compatible
Cursor
Copilot
ChatGPT
Gemini
Acerca de

EXPERIMENTAL, opt-in memory self-improvement for long-lived ADK agents — relevance-conditioned preload, the periodic consolidation "dream" pass, the after-turn judge fork, fire-and-forget sibling runs, per-session throttling, and the skill curator that proposes SKILL.md files. Read before enabling any NUVEL_MEMORY_* or NUVEL_SKILL* flag, when budgeting the extra LLM calls these add per turn, or wh

Palabras clave
skillclaude