Household Memory Keepsake
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Household Memory KeepsakeWhere did we store the camping lantern?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Household Memory Keepsake
Household Memory Keepsake is a self-hosted MCP server for a shared, persistent family memory. It helps track where things are, warranty dates, chores, and a record of who said what and when across the household.
This repository contains:
a TypeScript API server for memory storage and MCP endpoints
a PostgreSQL + Drizzle data layer
a React web app for the household memory UI
generated API schema/client code used across the workspace
Features
persistent household memory records
item location and ownership tracking
warranty and replacement timing reminders
chore tracking and family task history
shared house notes with timestamps and attribution
MCP-compatible API for AI assistants and tooling
Related MCP server: memory-mcp
Tech stack
Node.js 24
TypeScript 5.9
pnpm workspaces
Express 5
PostgreSQL + Drizzle ORM
React + Vite + Tailwind CSS
Zod validation
Repository layout
artifacts/api-server/— Express API server entry point and MCP routesartifacts/household-memory/— React front-end applib/db/— database schema and Drizzle client setuplib/api-spec/— API contract definitionslib/api-zod/— generated Zod validation schemaslib/api-client-react/— generated React API clientscripts/— utility scripts
Prerequisites
Before you start, install:
Node.js 24+
pnpm
PostgreSQL 14+ (or a compatible Postgres instance)
Installation
Clone the repository and install dependencies:
git clone https://github.com/ShivangiBhargava/Household-Memory-keepsake.git
cd Household-Memory-keepsake
pnpm installEnvironment variables
Create a .env file in the project root and set the required values:
DATABASE_URL=postgresql://username:password@localhost:5432/household_memory
PORT=5000These values are used by the server and database layer.
If you are using a local Postgres instance, make sure the database exists and the user has permissions to create tables.
Database setup
Push the current schema to your database:
pnpm --filter @workspace/db run pushThis uses Drizzle and the configured database URL from DATABASE_URL.
Run the app
1) Start the API server
pnpm --filter @workspace/api-server run devThis starts the Express server on the port defined by PORT (default usage in the repo is port 5000).
2) Start the frontend
Open a second terminal and run:
pnpm --filter @workspace/household-memory run devThis starts the Vite app for the household memory UI.
If you need the UI exposed on a network address, the package script already runs Vite with --host 0.0.0.0.
Build and typecheck
Run the full workspace checks:
pnpm run typecheckBuild the monorepo:
pnpm run buildAPI and code generation
If the OpenAPI or generated types change, regenerate the client and schemas:
pnpm --filter @workspace/api-spec run codegenProduction notes
For a deployed environment, set the same environment variables in your runtime environment and ensure your database is reachable from the app host.
License
This project is licensed under the MIT License. See the LICENSE file in the repository root for details.
Contributing
Contributions are welcome. Please open an issue or submit a pull request with a clear explanation of the change and any required migration or setup notes.
This server cannot be deployed
Maintenance
Related MCP Connectors
Governed personal world model and memory for your AI agent. Pair once, connect over MCP.
Persistent personal memory for AI assistants — save, search, and recall across every MCP client.
Private-by-default, local-first memory/context/task orchestrator for MCP apps and agents.
Persistent AI memory shared across Claude, ChatGPT, coding agents, and compatible MCP clients.
Related MCP Servers
AlicenseNot gradedqualityBmaintenanceEnables persistent memory storage and retrieval for MCP clients, allowing AI assistants to remember facts and context across conversations.14 npmMIT- AlicenseAqualityDmaintenanceProvides persistent memory for AI assistants via MCP, enabling them to store and recall facts, preferences, and tasks across conversations using either local file storage or a cloud backend with semantic search.54 npmMIT
- AlicenseNot gradedqualityBmaintenanceProvides a self-hosted shared memory service that lets AI agents capture and recall durable facts, decisions, and context across multiple tools and MCP-capable clients.3MIT
- FlicenseNot gradedqualityBmaintenanceEnables AI agents to store, search, and resolve shared memories with full provenance, conflict detection, and an audit trail across MCP-compatible clients.-