https://github.com/shimo4228/agent-knowledge-cycle

A knowledge cycle for AI agents — one that grows with the people who shape it. Centered on the scarcity of human attention and judgment as agent capability grows; six phases keep behavior aligned with operator intent across sessions. ADRs, JSON schemas, and a dependency-free Python reference.

adr agent-alignment agent-framework agent-knowledge-cycle agent-memory agent-rules agentic-ai ai-agent ai-agents anthropic claude claude-code cognitive-economy harness human-in-the-loop llm llm-agent memory-architecture signal-first specifications

Last synced: 06 Jun 2026