thedotmack/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
📊 Progressive Disclosure - Layered memory retrieval with token cost visibility
🔍 Skill-Based Search - Query your project history with mem-search skill (~2,250 token savings)
🖥️ Web Viewer UI - Real-time memory stream at http://localhost:37777
🔒 Privacy Control - Use <private> tags to exclude sensitive content from storage
⚙️ Context Configuration - Fine-grained control over what context gets injected
🤖 Automatic Operation - No manual intervention required
🔗 Citations - Reference past decisions with claude-mem:// URIs
🧪 Beta Channel - Try experimental features like Endless Mode via version switching

Documentation

📚 View Full Documentation - Browse markdown docs on GitHub

💻 Local Preview: Run Mintlify docs locally:

cd docs
npx mintlify dev

Getting Started

Installation Guide - Quick start & advanced installation
Usage Guide - How Claude-Mem works automatically
Search Tools - Query your project history with natural language
Beta Features - Try experimental features like Endless Mode

Best Practices

Context Engineering - AI agent context optimization principles
Progressive Disclosure - Philosophy behind Claude-Mem's context priming strategy

Architecture

Overview - System components & data flow
Architecture Evolution - The journey from v3 to v5
Hooks Architecture - How Claude-Mem uses lifecycle hooks
Hooks Reference - 7 hook scripts explained
Worker Service - HTTP API & PM2 management
Database - SQLite schema & FTS5 search
Search Architecture - Hybrid search with Chroma vector database

Configuration & Development

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

How It Works

┌─────────────────────────────────────────────────────────────┐
│ Session Start → Inject recent observations as context      │
└─────────────────────────────────────────────────────────────┘
                            ↓
┌─────────────────────────────────────────────────────────────┐
│ User Prompts → Create session, save user prompts           │
└─────────────────────────────────────────────────────────────┘
                            ↓
┌─────────────────────────────────────────────────────────────┐
│ Tool Executions → Capture observations (Read, Write, etc.)  │
└─────────────────────────────────────────────────────────────┘
                            ↓
┌─────────────────────────────────────────────────────────────┐
│ Worker Processes → Extract learnings via Claude Agent SDK   │
└─────────────────────────────────────────────────────────────┘
                            ↓
┌─────────────────────────────────────────────────────────────┐
│ Session Ends → Generate summary, ready for next session     │
└─────────────────────────────────────────────────────────────┘

Core Components:

5 Lifecycle Hooks - SessionStart, UserPromptSubmit, PostToolUse, Stop, SessionEnd (6 hook scripts)
Smart Install - Cached dependency checker (pre-hook script, not a lifecycle hook)
Worker Service - HTTP API on port 37777 with web viewer UI and 10 search endpoints, managed by PM2
SQLite Database - Stores sessions, observations, summaries with FTS5 full-text search
mem-search Skill - Natural language queries with progressive disclosure (~2,250 token savings vs MCP)
Chroma Vector Database - Hybrid semantic + keyword search for intelligent context retrieval

See Architecture Overview for details.

mem-search Skill

Claude-Mem provides intelligent search through the mem-search skill that auto-invokes when you ask about past work:

How It Works:

Just ask naturally: "What did we do last session?" or "Did we fix this bug before?"
Claude automatically invokes the mem-search skill to find relevant context
~2,250 token savings per session start vs MCP approach

Available Search Operations:

Search Observations - Full-text search across observations
Search Sessions - Full-text search across session summaries
Search Prompts - Search raw user requests
By Concept - Find by concept tags (discovery, problem-solution, pattern, etc.)
By File - Find observations referencing specific files
By Type - Find by type (decision, bugfix, feature, refactor, discovery, change)
Recent Context - Get recent session context for a project
Timeline - Get unified timeline of context around a specific point in time
Timeline by Query - Search for observations and get timeline context around best match
API Help - Get search API documentation

Example Natural Language Queries:

"What bugs did we fix last session?"
"How did we implement authentication?"
"What changes were made to worker-service.ts?"
"Show me recent work on this project"
"What was happening when we added the viewer UI?"

See Search Tools Guide for detailed examples.

Beta Features & Endless Mode

Claude-Mem offers a beta channel with experimental features. Switch between stable and beta versions directly from the web viewer UI.

How to Try Beta

Open http://localhost:37777
Click Settings (gear icon)
In Version Channel, click "Try Beta (Endless Mode)"
Wait for the worker to restart

Your memory data is preserved when switching versions.

Endless Mode (Beta)

The flagship beta feature is Endless Mode - a biomimetic memory architecture that dramatically extends session length:

The Problem: Standard Claude Code sessions hit context limits after ~50 tool uses. Each tool adds 1-10k+ tokens, and Claude re-synthesizes all previous outputs on every response (O(N²) complexity).

The Solution: Endless Mode compresses tool outputs into ~500-token observations and transforms the transcript in real-time:

Working Memory (Context):     Compressed observations (~500 tokens each)
Archive Memory (Disk):        Full tool outputs preserved for recall

Expected Results:

~95% token reduction in context window
~20x more tool uses before context exhaustion
Linear O(N) scaling instead of quadratic O(N²)
Full transcripts preserved for perfect recall

Caveats: Adds latency (60-90s per tool for observation generation), still experimental.

See Beta Features Documentation for details.

What's New

v6.4.9 - Context Configuration Settings:

11 new settings for fine-grained control over context injection
Configure token economics display, observation filtering by type/concept
Control number of observations and which fields to display

v6.4.0 - Dual-Tag Privacy System:

<private> tags for user-controlled privacy - wrap sensitive content to exclude from storage
System-level <claude-mem-context> tags prevent recursive observation storage
Edge processing ensures private content never reaches database

v6.3.0 - Version Channel:

Switch between stable and beta versions from the web viewer UI
Try experimental features like Endless Mode without manual git operations

Previous Highlights:

v6.0.0: Major session management & transcript processing improvements
v5.5.0: mem-search skill enhancement with 100% effectiveness rate
v5.4.0: Skill-based search architecture (~2,250 tokens saved per session)
v5.1.0: Web-based viewer UI with real-time updates
v5.0.0: Hybrid search with Chroma vector database

See CHANGELOG.md for complete version history.

System Requirements

Node.js: 18.0.0 or higher
Claude Code: Latest version with plugin support
PM2: Process manager (bundled - no global install required)
SQLite 3: For persistent storage (bundled)

Key Benefits

Progressive Disclosure Context

Layered memory retrieval mirrors human memory patterns
Layer 1 (Index): See what observations exist with token costs at session start
Layer 2 (Details): Fetch full narratives on-demand via MCP search
Layer 3 (Perfect Recall): Access source code and original transcripts
Smart decision-making: Token counts help Claude choose between fetching details or reading code
Type indicators: Visual cues (🔴 critical, 🟤 decision, 🔵 informational) highlight observation importance

Automatic Memory

Context automatically injected when Claude starts
No manual commands or configuration needed
Works transparently in the background

Full History Search

Search across all sessions and observations
FTS5 full-text search for fast queries
Citations link back to specific observations

Structured Observations

AI-powered extraction of learnings
Categorized by type (decision, bugfix, feature, etc.)
Tagged with concepts and file references

Multi-Prompt Sessions

Sessions span multiple user prompts
Context preserved across /clear commands
Track entire conversation threads

Configuration

Model Selection:

./claude-mem-settings.sh

Environment Variables:

CLAUDE_MEM_MODEL - AI model for processing (default: claude-haiku-4-5)
CLAUDE_MEM_WORKER_PORT - Worker port (default: 37777)
CLAUDE_MEM_DATA_DIR - Data directory override (dev only)

See Configuration Guide for details.

Development

# Clone and build
git clone https://github.com/thedotmack/claude-mem.git
cd claude-mem
npm install
npm run build

# Run tests
npm test

# Start worker
npm run worker:start

# View logs
npm run worker:logs

See Development Guide for detailed instructions.

Troubleshooting

Quick Diagnostic:

If you're experiencing issues, describe the problem to Claude and the troubleshoot skill will automatically activate to diagnose and provide fixes.

Common Issues:

Worker not starting → npm run worker:restart
No context appearing → npm run test:context
Database issues → sqlite3 ~/.claude-mem/claude-mem.db "PRAGMA integrity_check;"
Search not working → Check FTS5 tables exist

See Troubleshooting Guide for complete solutions.

Contributing

Contributions are welcome! Please:

Fork the repository
Create a feature branch
Make your changes with tests
Update documentation
Submit a Pull Request

See Development Guide for contribution workflow.

License

This project is licensed under the GNU Affero General Public License v3.0 (AGPL-3.0).

See the LICENSE file for full details.

What This Means:

You can use, modify, and distribute this software freely
If you modify and deploy on a network server, you must make your source code available
Derivative works must also be licensed under AGPL-3.0
There is NO WARRANTY for this software

Support

Documentation: docs/
Issues: GitHub Issues
Repository: github.com/thedotmack/claude-mem
Author: Alex Newman (@thedotmack)

Built with Claude Agent SDK | Powered by Claude Code | Made with TypeScript

Generated Insights

About claude-mem