judahpaul16/gpt-home

ChatGPT at home! A better alternative to commercial smart home assistants, built on the Raspberry Pi using LiteLLM and LangGraph.

What it solves

GPT Home transforms a Raspberry Pi into a voice-controlled AI home assistant, serving as a self-hosted alternative to devices like Google Nest Hub or Amazon Alexa. It integrates LLM-powered intelligence with home automation and personal productivity tools.

How it works

The project uses a combination of hardware (Raspberry Pi, microphone, speaker) and a software stack deployed via Docker. It leverages LiteLLM to provide a unified interface for over 100 LLM providers (such as OpenAI, Anthropic, and Google) and LangGraph for agentic workflow management. For persistent memory, it utilizes a PostgreSQL database with the pgvector extension.

Who it’s for

Hardware enthusiasts and DIYers who want a private, customizable AI home assistant that can control their home environment and manage their schedule.

Highlights

  • Broad Integration Support: Connects with Spotify, Philips Hue, OpenWeatherMap, Open-Meteo, and CalDAV calendars.
  • Personal Productivity: Built-in support for alarms, reminders, and to-do lists.
  • Flexible LLM Backend: Supports a wide variety of models via LiteLLM.
  • Hardware Agnostic: While optimized for Raspberry Pi, it can run on any Linux system.
  • Visual Feedback: Supports various display options, including I2C OLED and HDMI touchscreens.

Related

  • Project
    syxanash/maxheadbox

    A voice-activated, 100% local LLM agent for Raspberry Pi that can be extended with custom tools to automate hardware actions.

  • Project
    PiSugar/whisplay-ai-chatbot

    A pocket-sized AI chatbot device built on Raspberry Pi that enables voice-to-voice interaction, image generation, and local AI acceleration.

  • Project
    AndraxDev/speak-gpt

    An open-source AI assistant client for Android and web that allows users to connect multiple LLM providers using their own API keys.

  • Project
    szczyglis-dev/py-gpt

    A comprehensive desktop AI assistant that integrates multiple LLM providers and local models, featuring RAG for document chat, image/video generation, and a plugin-based automation system.

  • Project
    BerriAI/litellm

    LiteLLM is an open‑source Python SDK and self‑hosted proxy that provides a unified, OpenAI‑compatible API for calling over 100 LLM providers. It offers production features like virtual keys, spend tracking, guardrails, auto‑routing, and an admin dashboard, letting teams swap models or providers without code changes.