claude-mem

Persistent memory compression system built for Claude Code.

Quick Start • How It Works • Search Tools • Documentation • Configuration • Troubleshooting • License

Claude-Mem seamlessly preserves context across sessions by automatically capturing tool usage observations, generating semantic summaries, and making them available to future sessions. This enables Claude to maintain continuity of knowledge about projects even after sessions end or reconnect.

---

Quick Start

Start a new Claude Code session in the terminal and enter the following commands:

> /plugin marketplace add thedotmack/claude-mem

> /plugin install claude-mem

Restart Claude Code. Context from previous sessions will automatically appear in new sessions.

Key Features:

• 🧠 Persistent Memory - Context survives across sessions via direct SQLite storage
• 🔍 Semantic Search - sqlite-vec + sqlite-lembed for on-demand vector search
• 🖥️ Web Viewer UI - Browse history at http://localhost:37777 (run npm run viewer)
• 🔒 Privacy Control - Use <private> tags to exclude sensitive content from storage
• 🤖 Automatic Operation - No manual intervention required, no daemon to manage
• ⚡ Lightweight - No PM2, no Python, no external services - just SQLite
• 🧹 Deterministic - No LLM on write path, fast synchronous storage

---

Documentation

📚 View Full Documentation - Browse markdown docs on GitHub

Note: Some documentation may reference the pre-v8.0 architecture. The current simplified architecture uses direct SQLite access with sqlite-vec for vector search.

Getting Started

• Installation Guide - Quick start & advanced installation
• Usage Guide - How Claude-Mem works automatically

Architecture

• Hooks Architecture - How Claude-Mem uses lifecycle hooks
• Database - SQLite schema & vector search

Configuration & Development

• Configuration - Environment variables & settings
• Development - Building, testing, contributing
• Troubleshooting - Common issues & solutions

---

How It Works