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 — a hot cache (MEMORY.md) held under three size caps, per-session handoffs (context/handoffs/), topical knowledge articles (knowledge/concepts/), and canonical rules (.claude/rules/) — plus multi-project isolation via projects/<name>/ and an experiments/ sandbox. /close-session runs the end-of-session audit ritual. Zero external dependencies.
$npx -y skills add awrshift/claude-memory-kit --skill claude-memory-kitInstalls into the current project.
Run `npx skills use "https://github.com/awrshift/claude-memory-kit" --skill "awrshift/claude-memory-kit"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/awrshift/claude-memory-kit" that are relevant to the current task. Run `npx skills add "https://github.com/awrshift/claude-memory-kit"` and select the relevant skills, then follow their instructions.