Mcp

net.modelbrainv0.1.0Updated Oct 4, 2026

Local memory for AI assistants: remember, recall, forget and expand, stored on your own computer.

VerifiedSTDIODesktop onlyKnowledge & Memory

Overview

AI-generated overview

A local memory server that lets an AI assistant remember, recall, forget, and expand stored information on your own computer.

What it does
This MCP server provides local memory for AI assistants. Based on its description, it exposes tools to remember information, recall it later, forget stored items, and expand on what has been saved. Memory is kept on the user's own machine rather than in a hosted service.
When to use it
Worth considering when you want an assistant to carry context across sessions without sending that context to a third-party memory service. Suitable for users who prefer local storage of remembered information.
Requirements
Runs as a local process over stdio, installed from the npm package modelbrain-mcp, so a Node.js runtime is needed. Desktop only; no web execution. No authentication, environment variables, or headers are declared.
Before you install
The description says memory is stored on your own computer, so remembered content persists locally and should be reviewed or cleared with the forget capability when needed. No credentials, payments, or third-party data sharing are indicated in the available information.

Installation

In SourceWeft

  1. Open Mcp in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Tools

0
Tool metadata has not been indexed yet.

Version history

1
  1. v0.1.0LatestOct 4, 2026