Use Case
Three Tier Memory is a powerful AI agent skill that extends your assistant with new capabilities. Three-Tier Memory Management system. Used to manage the short-term, medium-term, and long-term memory of AI agents. Includes: (1) Sliding window short-term memory, (2) Automatic summary generation mid-term memory, (3) Vector retrieval long-term memory (RAG). Use this skill when you need to manage conversation history, optimize context, build a personal knowledge base, or implement memory persistence. This guide walks you through installing Three Tier Memory, configuring it for your setup, and running your first commands β so you can start getting value in minutes.
Install Three Tier Memory: npx clawhub@latest --dir ~/.claude/skills install monica-three-tier-memory
Restart your AI client (Claude Code, Cursor, Gemini CLI, or OpenClaw)
Type a natural language request related to documents & notes to trigger Three Tier Memory
Review the output and refine your prompt for better results
Combine Three Tier Memory with other skills to build multi-step workflows
Copy these prompts and use them with your AI agent after installing Three Tier Memory
Help me get started with Three Tier Memory
What can Three Tier Memory do for my documents & notes workflow?
Show me an example of using Three Tier Memory
Select your agent
Option 1: Install via CLI (recommended)
Recommended (no pre-install needed)
npx clawhub@latest --dir ~/.claude/skills install monica-three-tier-memoryOr via clawhub CLI (if already installed)
clawhub --dir ~/.claude/skills install monica-three-tier-memoryβ οΈ Requires Node.js 18+. No Node? Use Option 2 below to download the ZIP instead. Install Node.js β
Option 2: Manual install (no Node required)
Download the ZIP, extract it, and place the folder at the path below. Restart your agent to activate.
Install path
~/.claude/skills/monica-three-tier-memory/π‘Extract and place the folder at the path above, then restart your agent.