Skip to content

impactjo/home-memory

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1 Commit
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Home Memory

Ask your home.

Your AI assistant's memory for everything in and around your home.

MIT License .NET 10 22 MCP Tools


Home Memory is an MCP server that gives your AI assistant structured, persistent knowledge about your home — every room, every device, every pipe and cable, every item you own. It plugs into Claude, OpenClaw, or any MCP-compatible AI and turns natural conversation into a living, queryable documentation of your home and everything in it.

No app to learn. No forms to fill out. No UI needed — the AI is your interface.

Tell your AI about your heat pump, your car, your power tools, or your wine collection — it extracts the relevant details and stores them as structured data in your local database. Snap a photo of a device or hand it an invoice — same thing. Ask "What's in the basement?" or "When is my car due for inspection?" and get real answers from real data, not hallucinations.

Demo: One sentence creates two elements — Claude finds the right categories, creates a missing room, and documents everything.

What you can do

Document anything by just talking:

"I have a Daikin Altherma heat pump in the utility room."

Your AI finds the right category, resolves the location, and creates the element — no manual data entry.

"My car is a 2023 Toyota Corolla Hybrid — next inspection is due in March."

Not just building infrastructure — vehicles, tools, appliances, valuables, anything that belongs to you.

Ask questions about your home:

"What's in the basement?" · "Show me all planned purchases." · "Where is my washing machine?"

Upload a photo and let your AI identify it:

(attach a photo of a device) "What is this? Add it to the utility room."

Vision-capable AIs recognize the device and create the element via MCP.

Read an invoice and extract devices:

(attach a PDF invoice) "Extract the installed devices and add them to my home."

Track connections between elements:

"The circuit breaker panel feeds the kitchen outlet via NYM-J 3x1.5."

Cable routes, pipe runs, duct paths — documented as connections between elements.

Plan renovations:

"We're planning a PV system on the roof." · "The old oil heater was removed last year."

Track what's planned, what exists, and what's been removed.

Quick Start

Option 1: Download Release (recommended)

  1. Download the latest release ZIP from GitHub Releases
  2. Extract to any folder
  3. Register the MCP server:

Claude Code:

claude mcp add home-memory --scope user -- "/path/to/HomeMemoryMCP.exe"

OpenAI Codex CLI:

codex mcp add home-memory -- "/path/to/HomeMemoryMCP.exe"
  1. Start your AI client — done.

On first launch, Home Memory automatically creates a local database at %LOCALAPPDATA%\HomeMemory\homememory.scd with over 100 categories and a default house structure. No setup wizard, no configuration needed — just start talking, and adapt everything to your home through conversation. To change the database location, set the HOME_MEMORY_DB_PATH environment variable (see Configuration).

Option 2: Build from Source

Requires .NET 10 SDK and Firebird 3.0.

git clone https://github.com/impactjo/home-memory.git
cd home-memory
dotnet publish HomeMemoryMCP -c Release

See Setup Guide for details on Firebird configuration and environment variables.

How it works

You ──── AI Assistant ──── Home Memory MCP ──── Local Database
              (natural language)      (22 tools)       (Firebird Embedded)

Home Memory implements the Model Context Protocol (MCP), an open standard that lets AI assistants use external tools. When you talk to your AI about your home, it calls Home Memory's tools behind the scenes — reading, creating, updating, and searching your home data.

Your data stays local. The database is a single file on your machine. Nothing is sent anywhere except to the AI you're already talking to.

Features

22 MCP Tools

Tools What they do
Explore get_structure_overview, find_element, list_elements, get_element_details Browse your home, search by name/path/status, get full details
Manage Elements create_element, update_element, delete_element, move_element Add devices, furniture, fixtures — or entire rooms and floors
Connections get_connections, get_connection_details, create_connection, update_connection, delete_connection Document physical lines: cables, pipes, ducts, conduits
Categories list_categories, get_by_category, create_category, update_category, delete_category Over 100 built-in categories across all domains
Status list_statuses, create_status, update_status, delete_status Track what's existing, planned, or removed

Covers every domain

Electrical (circuits, PV, wallbox, home automation) · HVAC · Plumbing · IT & Communications · Security (alarm, fire, surveillance) · Building Materials · Landscaping (garden, pool, irrigation) · Household (appliances, furniture, valuables) · Vehicles · Tools · Health · Sports & Leisure

Smart defaults

  • Over 100 categories organized by trade and domain — from circuit breakers to garden sprinklers to vehicles
  • Default house structure with floors, rooms, garage, and outdoor areas — customize by talking to your AI
  • Auto-setup on first run — no manual database creation needed
  • Flexible naming — your AI can use "Ground Floor" or "GF", the server resolves both

Compatibility

Client Status
Claude Code (CLI) Tested, production-ready
OpenAI Codex CLI Tested, production-ready
OpenClaw Compatible — add as MCP server in openclaw.json
Any MCP-compatible client Should work (stdio transport)

The release ZIP is a self-contained Windows build with all dependencies included (no .NET or Firebird installation required). On macOS and Linux, you can build from source with .NET 10 and Firebird 3 — see the Setup Guide for details.

Configuration

Environment Variable Purpose Default
HOME_MEMORY_DB_PATH Database file location %LOCALAPPDATA%\HomeMemory\homememory.scd (Windows) · ~/.local/share/HomeMemory/homememory.scd (Linux) · ~/Library/Application Support/HomeMemory/homememory.scd (macOS)
HOME_MEMORY_FBCLIENT Path to Firebird client library Bundled with release / Firebird installation

Roadmap

  • Demo database with sample data
  • DXT packaging for Claude Desktop Extensions

Architecture

  • .NET 10 with ModelContextProtocol SDK
  • Firebird Embedded — zero-install database engine, single-file storage
  • Raw SQL with recursive CTEs — no ORM overhead, transparent and auditable
  • Semantic Versioning — currently v0.1.0 (pre-release)

Contributing

Home Memory is in its early stages and we'd love to hear from you! Right now, the best way to contribute is:

  • Open an issue for bug reports, feature ideas, or questions
  • Share your use case — how are you using Home Memory? What's missing?
  • Spread the word if you find it useful

We're not accepting code contributions at this point. If you'd like to build and explore the code locally, see the Setup Guide.

Background — Smartconstruct

Home Memory is the AI-native access layer to a proven data model from Smartconstruct, a Windows desktop application for documenting physical assets — from building infrastructure and home installations to household items, vehicles, and tools. The MCP server shares the same database schema — a domain model refined through real-world use in residential construction projects.

The Home Memory database can be opened directly in Smartconstruct, giving you a full desktop UI with additional capabilities: image and document references (stored as file paths), part types and templates, company records, and printable reports. Smartconstruct is currently available in German. If you're interested in an English version, please open an issue — your feedback helps us prioritize.

License

MIT

About

Ask your home. Your AI assistant's memory for everything in and around your home.

Topics

Resources

License

Stars

Watchers

Forks

Packages

 
 
 

Languages