Memory MCP

🧠 Memory MCP

Give your AI assistant a persistent second brain

🚀 Quick Start

Stop re-explaining your project every session. Memory MCP learns what matters and keeps it ready — instant recall for the stuff you use most, semantic search for everything else.

✨ Features

• Two-tier architecture: A hot cache (0ms) for frequently-used knowledge auto-injected into context and a cold storage (~50ms) searchable by meaning via semantic similarity.
• Self-organizing: Automatically learns and promotes frequently-used memories, no manual curation required.
• Project-aware: Auto-isolates memories by git repo.
• Knowledge graph: Connects related concepts for multi-hop recall.
• Pattern mining: Learns from Claude's outputs.
• Trust scoring: Demotes outdated facts.
• Easy setup: One command to install, local SQLite storage.

📦 Installation

# Install package
uv tool install hot-memory-mcp   # or: pip install hot-memory-mcp

# Add plugin (recommended)
claude plugins add michael-denyer/memory-mcp

The plugin gives you auto-configured hooks, slash commands, and the Memory Analyst agent. MLX is auto-detected on Apple Silicon.

{
  "mcpServers": {
    "memory": {
      "command": "memory-mcp"
    }
  }
}

Restart Claude Code. The hot cache auto-populates from your project docs.

⚠️ Important Note

First run: Embedding model (~90MB) downloads automatically. Takes 30-60 seconds once.

💻 Usage Examples

Basic Usage

flowchart LR
    subgraph LLM["Claude"]
        REQ((Request))
    end

    subgraph Hot["HOT CACHE · 0ms"]
        HC[Session context]
        PM[(Promoted memories)]
    end

    subgraph Cold["COLD STORAGE · ~50ms"]
        VS[(Vector search)]
        KG[(Knowledge graph)]
    end

    REQ -->|"auto-injected"| HC
    HC -.->|"draws from"| PM
    REQ -->|"recall()"| VS
    VS <-->|"related"| KG

The hot cache (~10 items) is injected into every request — it combines recent recalls, predicted next memories, and top promoted items. Promoted memories (~20 items) is the backing store of frequently-used memories. Memories used 3+ times auto-promote; unused ones demote after 14 days.

📚 Documentation

Before & After

What Makes It Different

Most memory systems make you pay a tool-call tax on every lookup. Memory MCP's hot cache bypasses this entirely — your most-used knowledge is already in context when Claude starts thinking.

Quick Reference

See Reference for all 14 slash commands and full tool API.

Dashboard

memory-mcp-cli dashboard    # Opens at http://localhost:8765

Browse memories, hot cache, mining candidates, sessions, and knowledge graph.

How to Use

Memory MCP is designed to run as three complementary components:

The plugin is recommended for most users — it auto-configures the MCP server and adds productivity features. Run the dashboard alongside when you want visibility into what's being stored.

📄 License

MIT