Smart Home Solutions
Real-time Automation

Control Every Room. Intelligently.

A unified smart home platform connecting every switch, sensor, and scene — orchestrated by real-time WebSockets and an AI assistant that understands natural language.

4+Device Types
Real-timeWebSocket Sync
AILangGraph NLU
Current Home Temperature22°C
Active
6 devices online
LIVING ROOMBEDROOMKITCHENBATHROOM12.0m8.0m
On
Living Room4 devices
On
Bedroom2 devices
Off
Kitchen3 devices
Platform Capabilities

Everything Your Home Needs

Built on a production-grade stack — not a prototype. Every feature is designed for reliability, extensibility, and day-to-day use.

Active

Device Control

Manage smart switches with granular on/off, manual/auto modes, and load-level slider (0–1000) — all synced in real time across every client.

Organized

Room Management

Structure your home as Homes → Rooms → Devices. Bulk-control entire rooms or drill down to individual channels with a tap.

Live

Real-time Sync

Bidirectional WebSocket events dispatch commands and surface device responses in under 50ms — no polling, no stale state.

Beta

AI Assistant

LangGraph-powered NLU understands intent and entities in natural language — turn on lights, set scenes, or query energy usage conversationally.

Setup in Minutes

How It Works

01
ESP32MASTERD1 CH1D1 CH2D1 CH3BACKENDAPIGatewaySlave Nodes

Connect Your Devices

Flash the WemosD1 slave firmware and pair each switch module to the ESP32 master gateway. The gateway joins your local network and establishes a persistent WebSocket tunnel to the backend.

ESP32 + WemosD1 Firmware · WebSocket
02
HOMELIVING RMBEDROOMSW 01SW 02SW 03

Organize Rooms & Scenes

Log in with your account, create a Home, then group devices into Rooms. Assign names, icons, and default modes (manual / auto). Changes propagate to every connected client instantly.

JWT Auth · Flutter App · Real-time Sync
03
Turn off bedroom lightsIntent: control_device✓ Bedroom: 2 devices off

Talk to Your Home

Ask the AI assistant anything: 'Turn off all bedroom lights' or 'What is the kitchen power usage today?' LangGraph resolves intent, extracts entities, and dispatches the right device commands — safely.

LangGraph · gpt-4o-mini · Safety Controls
AI Assistant · Beta

Your Home Understands You

Built on LangGraph with OpenAI's gpt-4o-mini at its core, the AI assistant interprets natural language across multi-turn conversations to control devices, query analytics, and manage automations — with safety guardrails at every step.

Natural Language Control

Phrase commands in plain English — intents and entities are extracted automatically.

Multi-turn Context

The assistant remembers conversation history to handle follow-up questions naturally.

Safety Guardrails

All commands pass through invariant checks before execution to prevent unintended states.

Analytics Queries

Ask for energy summaries, device uptime leaderboards, or trend analysis by room.

AI
Home AssistantOnline

Hey, can you set the living room to movie mode?

Sure — dimming living room lights to 30% and closing the smart blinds.

control_device · 3 actions

What's today's energy usage so far?

You've consumed 4.2 kWh today. Kitchen is your top draw at 1.8 kWh.

analytics_query
Ask your home anything...
Under the Hood

Built on a Modern Stack

Each layer of the platform was chosen for production reliability — from IoT firmware to AI orchestration.

FastAPIBackend
PostgreSQLDatabase
SQLAlchemy 2.0ORM
AlembicMigrations
WebSocketTransport
FlutterMobile
RiverpodState
ESP32Hardware
WemosD1Hardware
LangGraphAI
gpt-4o-miniAI
JWT + bcryptAuth
DockerDeploy
AWS LightsailCloud

The system uses a full real-time WebSocket bus — not REST polling — so device state changes appear on every connected client (mobile, web, legacy Android) within milliseconds, regardless of which client sent the command.

Start Automating Today

Open-source, self-hostable, and production-ready. Deploy the backend with Docker in minutes and start pairing your first device.