amem

Persist a memory with intelligence — classify, dedupe against existing memories, store with metadata, and link to related entries. Use when the user says "remember this", "save this", "don't forget", "keep this", "save it", or equivalent intent in any language. Do NOT fire for file saves, git commits, or code persistence — only knowledge/memory persistence.

Load full memory context for the current task. Use automatically at the start of coding tasks to load corrections, decisions, and relevant background. Also use when switching topics mid-session.

Run health diagnostics on the amem memory database. Use when the user wants to check memory health, embedding coverage, stale memories, or diagnose issues.

Export all memories as markdown or to a file. Use when the user wants to back up, share, or review their memories outside of amem.

List all memories, optionally filtered by type. Use when the user wants to browse their stored memories or see what's in a specific category.

Search memories quickly. Use when the user asks "what do you remember about", "recall", "search memory", or wants to find past decisions, corrections, or context.

Store a memory quickly. Use when the user says "remember this", "store this", "don't forget", or wants to save a correction, decision, pattern, or preference.

Show amem memory statistics — total count, type breakdown, confidence distribution, embedding coverage. Use when the user asks about memory stats, counts, or wants an overview.

Export all memories as markdown or to a file. Use when the user wants to back up, share, or review their memories outside of amem.

Install or uninstall amem lifecycle hooks for automatic memory capture in Claude Code. Captures tool observations, auto-summarizes sessions, and injects context at startup.

Auto-configure amem for all detected AI tools (Claude Code, Cursor, Windsurf, GitHub Copilot). Use when the user wants to set up amem or configure it for their tools.

List all memories, optionally filtered by type. Use when the user wants to browse their stored memories or see what's in a specific category.

Generate auto-extraction rules for AI tools. Writes guidelines to CLAUDE.md, .cursorrules, etc. that teach the AI when and how to store memories. Use when the user wants to set up proactive memory extraction.

Show amem memory statistics — total count, type breakdown, confidence distribution, embedding coverage. Use when the user asks about memory stats, counts, or wants an overview.

Export shareable memories for teammates. Filters out private/personal data and creates a JSON file that teammates can import. Use when the user wants to share project knowledge with their team.

Import a teammate's exported memory file. Deduplicates automatically and lowers confidence slightly for second-hand knowledge. Use when the user receives a team memory export to import.

Run health diagnostics on the amem memory database. Use when the user wants to check memory health, embedding coverage, stale memories, or diagnose issues.

Load full memory context for the current task. Use automatically at the start of coding tasks to load corrections, decisions, and relevant background. Also use when switching topics mid-session.

Open the amem web dashboard. Use when the user wants to see their memories visually, browse the knowledge graph, or manage memories via a web UI.

Search memories quickly. Use when the user asks "what do you remember about", "recall", "search memory", or wants to find past decisions, corrections, or context.

Import Claude Code auto-memory into amem. Use when the user wants to sync, import, or merge their Claude auto-memory with amem's structured memory.