Agent Memory MCP Server 🧠

Persistent memory for AI agents — store, retrieve and search knowledge across sessions. No more forgetting between conversations.

The Problem

AI agents lose all context when a session ends. This MCP server gives agents a persistent knowledge store that survives across sessions, tools, and even different agent frameworks.

Features

• Store & Retrieve — Key-value storage with full persistence
• Namespaces — Separate memories by project, user, or context
• Tags — Categorize memories for easy filtering
• Full-Text Search — Search across all stored knowledge
• Access Tracking — See which memories are accessed most
• Statistics — Dashboard showing memory usage

Installation

pip install agent-memory-mcp-server

Usage with Claude Code

{
  "mcpServers": {
    "memory": {
      "command": "uvx",
      "args": ["agent-memory-mcp-server"]
    }
  }
}

Tools

Examples

"Remember that the user prefers dark mode"
"What do you know about Project Alpha?"
"Store this API response for later"
"What were the key decisions from last session?"

How It Works

Uses SQLite for zero-configuration persistent storage. Data is stored locally — no cloud, no API keys, no costs. The database file (memory.db) is created automatically in the server directory.

License

MIT