Memorymesh

Overview

Memorymesh is a Model Context Protocol (MCP) server: Persistent, zero-dependency AI memory using SQLite. Local-first, cross-tool portable. Because it speaks the Model Context Protocol, AI assistants can use Memorymesh as a set of callable tools instead of you copy-pasting between apps.

It runs locally: the Python package memorymesh (via uvx) speaks MCP over stdio on your machine. No credentials are required — it works out of the box. The current release is v4.1.0.

On mcp.site, Memorymesh sits in the Memory category. Any MCP client can use it — Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed among them — via the install snippets below. If you maintain Memorymesh for sparkvibe-io, claim this listing to verify ownership, earn the Verified badge, and keep the details current.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "memorymesh": {
      "command": "uvx",
      "args": [
        "memorymesh"
      ]
    }
  }
}