review

You can audit AI auto-memory by scanning memory directories, MEMORY.md, topic files, and CLAUDE.md to identify stale entries, consolidation opportunities, and promotion candidates for optimizing your AI knowledge base.

AI auto-memory optimization analyzes your knowledge base to prevent the accumulation of outdated or conflicting data, ensuring the AI's learned information remains accurate and efficient during development workflows.

Checking memory health metrics involves parsing memory files and project documentation like CLAUDE.md to report on file sizes and cross-references, providing actionable recommendations for knowledge base maintenance.

Yes, you can identify promotion candidates in Claude Code's auto-memory by performing a full memory analysis that scans associated files and directories to evaluate entries for potential knowledge base upgrades.

The best way to clean up outdated information is to run a comprehensive memory audit that parses topic files and cross-references project documentation to detect redundant entries and generate actionable optimization recommendations.