claude-memory-kit

@awrshift

Persistent memory for Claude Code agents with an agent-audit-ritual architecture. User only talks; the agent captures, audits, proposes promotions, and writes. Memory lives in layers — daily logs, hot cache (MEMORY.md), topical knowledge articles (knowledge/concepts/), and canonical rules (.claude/rules/) — plus multi-project isolation via projects/<name>/ and an experiments/ sandbox. /close-day runs the end-of-day audit ritual. Zero external dependencies.