adk-memory-self-improvement

SKILLWorkflowcommunity
v0.0.0Folken2MITUpdated 10d agoSource →

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 →
2Repo stars
1Clients
1Formats
10d agoLast update
Skill
AuthorFolken2
Version0.0.0
LicenseMIT
CategoryWorkflow
Formatsskill.md
PromptNot published
Compatibility
Claude✓ Supported
Cursor
Copilot
ChatGPT
Gemini
About

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

Keywords
skillclaude