Stats
Actions
Tags
From claude-mem
Explains how claude-mem captures observations, injects context, and where data is stored locally.
How this skill is triggered — by the user, by Claude, or both
Slash command
/claude-mem:how-it-worksThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Every Read, Edit, and Bash that Claude makes turns into a compressed observation. Observations get summarized at session end. Relevant ones get auto-injected into future prompts so the next session starts with context from the last one — no re-explaining the codebase, no re-discovering decisions.
Every Read, Edit, and Bash that Claude makes turns into a compressed observation. Observations get summarized at session end. Relevant ones get auto-injected into future prompts so the next session starts with context from the last one — no re-explaining the codebase, no re-discovering decisions.
Memory injection starts on your second session in a project.
The first session in a fresh project seeds memory; subsequent sessions receive auto-injected context for relevant past work. Run /learn-codebase if you want to front-load the entire repo into memory in a single pass (~5 minutes, optional).
Everything stays in ~/.claude-mem on this machine.
Nothing leaves your machine except calls to whichever AI provider you configured for compression (Claude / OpenRouter / Gemini). The SQLite database, vector index, logs, and settings all live under that directory and are removed cleanly on npx claude-mem uninstall.
npx claudepluginhub thedotmack/claude-mem --plugin claude-memProvides stable principles, keyword registry, and navigation for Claude Code memory system (CLAUDE.md, static memory, hierarchy, imports). Delegates details to docs-management skill.
Manages Claude Code persistent memory: CLAUDE.md hierarchy, rules in .claude/rules/, auto memory files, imports, bootstrap setup, debugging, and best practices.
Provides persistent cross-session memory for Claude Code using a two-layer architecture (hot cache + knowledge wiki), safety hooks, and end-of-day synthesis via /close-day.