Memorymesh MCP Server

io.github.sparkvibe-io/memorymesh

local only

Memorymesh runs on your own machine — the client starts it, so there is no endpoint to ping. 83 installs a week from pypi.

Persistent, zero-dependency AI memory using SQLite. Local-first, cross-tool portable.

Installs per day peak 46 · avg 14 · +9% w/w

a month agotoday

Installs / week

pypi · memorymesh

—

Stars

on GitHub

—

Last commit

0 releases in 90 days

—

License

language unknown

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add memorymesh -- uvx memorymesh

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "memorymesh": {
      "args": [
        "memorymesh"
      ],
      "command": "uvx"
    }
  }
}

~/.codex/config.toml

[mcp_servers.memorymesh]
command = "uvx"
args = ["memorymesh"]

.cursor/mcp.json

{
  "mcpServers": {
    "memorymesh": {
      "args": [
        "memorymesh"
      ],
      "command": "uvx"
    }
  }
}

.vscode/mcp.json

{
  "mcpServers": {
    "memorymesh": {
      "args": [
        "memorymesh"
      ],
      "command": "uvx"
    }
  }
}

Memorymesh — questions

Answers built from our own checks of this server.

Why is there no uptime for Memorymesh?

Memorymesh runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package memorymesh was installed 83 times last week.

How do I connect Memorymesh?

Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It runs locally, so the command pulls memorymesh straight from pypi; nothing to host, nothing to sign up for.

How many people use Memorymesh?

The pypi package memorymesh was installed 83 times in the last week. Week over week that is +9%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.