🧠 cmem

Your Claude Code Conversations, Remembered Forever

Don't just explore your code or folders—explore your conversations, or pick up where you left off.

Semantic search • Organize by project • Favorite conversations • 100% local

Get Started

npx @colbymchenry/cmem

_{Interactive installer configures Claude Code automatically}

---

Ever closed your terminal and lost that perfect Claude conversation? The one where you finally figured out that tricky bug, or designed that elegant architecture?

cmem gives Claude Code a long-term memory. Every conversation is automatically saved, indexed, and searchable—so you (and Claude) can pick up right where you left off.

MCP Integration

Using CMEM MCP to fetch conversational data about previous chat sessions

Claude can search through your conversation history and synthesize answers—all without cluttering your main session context.

---

Session Navigation

Easily navigate between previous chat sessions and pick back up right where you left off

Browse, search, filter, rename, and restore any conversation with the interactive TUI.

Open all previous chat sessions in current directory

Why cmem?

🧠 Sub-Agent Summarization — When Claude needs context from past sessions, cmem spawns a separate Claude instance to read and synthesize—keeping your main conversation context clean. Just like Explore agents, but for your conversation history.

🔍 Semantic Search — Find conversations by meaning, not keywords. "That React hooks discussion" or "the database migration plan" just works.

🤖 Claude Can Remember — Via MCP integration, Claude can search your past conversations. "What did we decide about auth last week?" Finally, context that persists.

🔄 Automatic Sync — A background daemon watches your Claude Code sessions and keeps everything indexed in real-time.

💾 Never Lost — Every conversation is automatically backed up. Even if Claude Code clears its storage, cmem restores your sessions instantly when you resume them.

📦 100% Local & Private — Everything runs on your machine. No cloud services, no API keys, no external servers. Just SQLite + local AI embeddings.

Quick Start

npx @colbymchenry/cmem

The setup wizard will:

1. Install cmem globally
2. Download the embedding model (~130MB, one-time)
3. Optionally set up auto-sync on login (macOS)
4. Configure MCP server in ~/.claude.json + permissions in ~/.claude/settings.json

That's it. Your conversations are now being remembered.

Requirements

• Node.js 18+

No other dependencies. The AI embedding model downloads automatically on first use and runs entirely in Node.js.

Usage

cmem                    # Browse sessions in beautiful TUI
cmem --local            # Browse sessions from current folder only
cmem search "query"     # Semantic search across all conversations
cmem watch              # Start the sync daemon
cmem stats              # See what's stored

How It Works

Claude Code sessions → cmem watch daemon → SQLite + Vector DB
                                                ↓
                              Claude Code ← MCP Server ← Semantic Search

1. Watch: The daemon monitors ~/.claude/ for new/changed sessions
2. Index: Conversations are parsed and embedded locally using nomic-embed-text-v1.5
3. Search: Query by meaning using vector similarity
4. Remember: Claude can access past conversations via MCP tools

Background Daemon

The cmem watch daemon runs in the background and automatically syncs your Claude Code sessions:

• With daemon installed: Sessions sync automatically whenever you use Claude Code
• Without daemon: Run cmem watch manually, or sessions sync when you open the TUI

On macOS, you can install the daemon to start automatically on login:

cmem install    # Enable auto-start
cmem uninstall  # Disable auto-start

MCP Tools

Once configured, Claude Code gains these abilities:

Tool	What it does
search_and_summarize	The star feature — Ask a question, get an AI-synthesized answer from past sessions
search_sessions	Find sessions by semantic similarity
list_sessions	Browse recent sessions
get_session	Retrieve full conversation history
get_session_context	Get context to continue a past conversation

How search_and_summarize Works

Main Claude Session                          cmem MCP Server
       │                                            │
       │  "What did we decide about auth?"          │
       ├───────────────────────────────────────────►│
       │                                            │
       │                                   ┌────────┴────────┐
       │                                   │ 1. Vector search │
       │                                   │ 2. Find sessions │
       │                                   │ 3. Read content  │
       │                                   └────────┬────────┘
       │                                            │
       │                                   ┌────────┴────────┐
       │                                   │ Spawn Claude CLI │
       │                                   │ (sub-agent)      │
       │                                   │                  │
       │                                   │ Reads sessions,  │
       │                                   │ synthesizes      │
       │                                   │ answer           │
       │                                   └────────┬────────┘
       │                                            │
       │  "Based on your Jan 15 session, you       │
       │   decided to use JWT with refresh..."      │
       │◄───────────────────────────────────────────┤
       │                                            │

This keeps your main context clean—only the concise summary comes back, not the raw session content. Uses Haiku by default for speed, configurable to Sonnet or Opus.

Commands

Command	Description
cmem	Launch interactive TUI
cmem --local	Launch TUI filtered to current folder
cmem setup	Run setup wizard
cmem search <query>	Semantic search
cmem list	List all sessions
cmem restore <id>	Output session context
cmem watch	Start sync daemon
cmem install	Auto-start daemon on login (macOS)
cmem uninstall	Remove auto-start
cmem stats	Storage statistics
cmem mcp	Start MCP server

TUI Views

Global Tab

All your sessions in one place, smart-sorted into three tiers:

1. Starred sessions — Your favorites, sorted by message count
2. Named sessions — Custom-named conversations, sorted by message count
3. Everything else — Sorted by message count

Press s to star/unstar a session.

Projects Tab

Browse sessions organized by project folder.

• Press Enter to drill into a project's sessions
• Press s to enter sort mode — use ↑/↓ to reorder, Enter to confirm
• Custom project order is persisted

TUI Keyboard Shortcuts

Key	Action
←/→ or h/l	Switch tabs (Global / Projects)
↑/↓ or j/k	Navigate
Enter	Resume session / Open project
s	Star session (Global) / Sort mode (Projects)
r	Rename session
R	Clear custom name
d	Delete session
/	Search (Global tab)
Esc	Back / Cancel
q	Quit

Data Storage

All data is stored locally in ~/.cmem/:

• sessions.db — SQLite database with vector embeddings
• models/ — Downloaded embedding model (~130MB)
• backups/ — Full copies of all conversation JSONLs (auto-restored if Claude deletes them)

Claude Code sessions are read from ~/.claude/.

Tech Stack

• SQLite + sqlite-vec — Embedded vector database
• transformers.js + nomic-embed-text-v1.5 — Local AI embeddings (768 dimensions, runs in Node.js)
• ink — Beautiful terminal UI (React for CLI)
• MCP — Model Context Protocol for Claude integration

License

MIT

---

Stop losing your best conversations.
npx @colbymchenry/cmem