GladysAssistant/Gladys

A privacy-first, open-source home assistant

What it solves

Gladys Assistant provides a privacy-first, open-source platform for managing and automating your smart home. It allows users to centralize control of their connected devices without relying on external cloud services that compromise data privacy.

How it works

Gladys runs as a local instance on your hardware, such as a Raspberry Pi, mini-PC, or NAS. It is designed to be deployed easily using Docker or Docker Compose, providing a dashboard interface to manage your home automation setup. The project is built and maintained by an active open-source community.

Who it’s for

It is for individuals who want to build a smart home system that keeps their data private and local. It is also for developers and contributors interested in building features or services for a home automation platform.

Highlights

  • Privacy-first architecture that keeps your data local.
  • Simple deployment via Docker and Docker Compose.
  • Compatible with various hardware, including Raspberry Pi, NAS, and mini-PCs.
  • Open-source project welcoming contributions in code, documentation, and translations.
  • Supports AI-assisted development for contributors.

Related

  • Project
    oxylabs/ai-crawler-py

    An AI-powered web crawler that uses natural language prompts to discover relevant pages and extract structured JSON or Markdown data from websites.

  • Project
    kingcharleslzy-ai/dsh-purge

    本机优先的 DSH 插件，消除反复确认、提供状态自检与快照回滚，令 AI 助手更连贯地执行学习/实验任务（改交互层，不改模型）。

  • Project
    Derpyu520/qq-bridge

    A Node.js bridge that connects QQ (via SnowLuma OneBot v11) to a DeepSeek Harness AI agent, providing chat, tool calls, role‑play, token‑usage dashboard, and a web console.

  • Project
    TanStack/ai

    TanStack AI is a TypeScript‑first, provider‑agnostic SDK that lets you build streaming chat, tool‑calling agents, structured‑output flows, multimodal generation (image, audio, video), realtime voice, and sandboxed code‑execution agents. It offers composable activities, type‑safe contracts (via Zod/Valibot/JSON Schema), adapters for many LLM providers (OpenAI, Anthropic, Gemini, Ollama, etc.), and framework‑native hooks for React, Vue, Solid, Svelte, and Preact. Tree‑shakable and observable, it’s aimed at developers who want a unified, type‑safe way to integrate generative AI into web and server apps.