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
• 🖥️ Web Viewer UI - Real-time memory stream at http://localhost:37777
• 💻 Claude Desktop Skill - Search memory from Claude Desktop conversations
• 🔒 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 observations with IDs (access via http://localhost:37777/api/observation/{id} or view all in the web viewer at http://localhost:37777)
• 🧪 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/public
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 & Bun 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:

1. 5 Lifecycle Hooks - SessionStart, UserPromptSubmit, PostToolUse, Stop, SessionEnd (6 hook scripts)
2. Smart Install - Cached dependency checker (pre-hook script, not a lifecycle hook)
3. Worker Service - HTTP API on port 37777 with web viewer UI and 10 search endpoints, managed by Bun
4. SQLite Database - Stores sessions, observations, summaries with FTS5 full-text search
5. mem-search Skill - Natural language queries with progressive disclosure
6. 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

Available Search Operations:

1. Search Observations - Full-text search across observations
2. Search Sessions - Full-text search across session summaries
3. Search Prompts - Search raw user requests
4. By Concept - Find by concept tags (discovery, problem-solution, pattern, etc.)
5. By File - Find observations referencing specific files
6. By Type - Find by type (decision, bugfix, feature, refactor, discovery, change)
7. Recent Context - Get recent session context for a project
8. Timeline - Get unified timeline of context around a specific point in time
9. Timeline by Query - Search for observations and get timeline context around best match
10. 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

Note

: Endless Mode is an experimental feature in the beta branch only. It is not included in the stable release you install via the marketplace. You must manually switch to the beta channel to try it, and it comes with significant caveats (see below).

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

1. Open http://localhost:37777
2. Click Settings (gear icon)
3. In Version Channel, click "Try Beta (Endless Mode)"
4. 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

Projected Results (based on theoretical modeling, not production measurements):

• Significant token reduction in context window
• More tool uses before context exhaustion
• Linear O(N) scaling instead of quadratic O(N²)
• Full transcripts preserved for perfect recall

Important Caveats:

• Not in stable release - You must switch to beta branch to use this feature
• Still in development - May have bugs, breaking changes, or incomplete functionality
• Slower than standard mode - Blocking observation generation adds latency to each tool use
• Theoretical projections - The efficiency claims above are based on simulations, not real-world production data

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
• Bun: JavaScript runtime and process manager (auto-installed if missing)
• uv: Python package manager for vector search (auto-installed if missing)
• 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

Settings are managed in ~/.claude-mem/settings.json. The file is auto-created with defaults on first run.

Available Settings:

Setting	Default	Description
CLAUDE_MEM_MODEL	claude-sonnet-4-5	AI model for observations
CLAUDE_MEM_WORKER_PORT	37777	Worker service port
CLAUDE_MEM_WORKER_HOST	127.0.0.1	Worker bind address (use 0.0.0.0 for remote access)
CLAUDE_MEM_DATA_DIR	~/.claude-mem	Data directory location
CLAUDE_MEM_LOG_LEVEL	INFO	Log verbosity (DEBUG, INFO, WARN, ERROR, SILENT)
CLAUDE_MEM_PYTHON_VERSION	3.13	Python version for chroma-mcp
CLAUDE_CODE_PATH	(auto-detect)	Path to Claude executable
CLAUDE_MEM_CONTEXT_OBSERVATIONS	50	Number of observations to inject at SessionStart

Settings Management:

# Edit settings via CLI helper
./claude-mem-settings.sh

# Or edit directly
nano ~/.claude-mem/settings.json

# View current settings
curl http://localhost:37777/api/settings

Settings File Format:

{
  "CLAUDE_MEM_MODEL": "claude-sonnet-4-5",
  "CLAUDE_MEM_WORKER_PORT": "37777",
  "CLAUDE_MEM_CONTEXT_OBSERVATIONS": "50"
}

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 → claude-mem 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.

Windows Known Issues

Console Window Visibility: On Windows, a console window may briefly appear when the worker service starts. This is a cosmetic issue that we're working to resolve. We've prioritized stability by removing a workaround that was causing libuv crashes. The window does not affect functionality and will be addressed in a future release when the MCP SDK provides proper window hiding support.

---

Bug Reports

Automated Bug Report Generator - Create comprehensive bug reports with one command:

# From the plugin directory
cd ~/.claude/plugins/marketplaces/thedotmack
npm run bug-report

The bug report tool will:

• 🌎 Auto-translate - Write in ANY language, automatically translates to English
• 📊 Collect diagnostics - Gathers versions, platform info, worker status, logs, and configuration
• 📝 Interactive prompts - Guides you through describing the issue with multiline support
• 🤖 AI formatting - Uses Claude Agent SDK to generate professional GitHub issues
• 🔒 Privacy-safe - Auto-sanitizes paths, optional --no-logs flag
• 🌐 Auto-submit - Opens GitHub with pre-filled title and body

Plugin Directory Paths:

• macOS/Linux: ~/.claude/plugins/marketplaces/thedotmack
• Windows: %USERPROFILE%\.claude\plugins\marketplaces\thedotmack

Options:

npm run bug-report --no-logs    # Skip logs for privacy
npm run bug-report --verbose    # Show all diagnostics
npm run bug-report --help       # Show help

---

Contributing

Contributions are welcome! Please:

1. Fork the repository
2. Create a feature branch
3. Make your changes with tests
4. Update documentation
5. 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).

Copyright (C) 2025 Alex Newman (@thedotmack). All rights reserved.

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