suyiiyii/AutoGLM-GUI

AutoGLM 的现代化 Web 图形界面 - 让 AI 自动化操作 Android 设备变得简单 已进化为你的专属自动化生产力工具

What it solves

AutoGLM-GUI provides a graphical interface and automation framework for controlling Android devices using AI. It transforms a mobile device into an AI-driven productivity tool, allowing users to execute complex tasks via natural language, schedule recurring actions, and manage multiple devices from a single dashboard without needing deep technical knowledge of ADB (Android Debug Bridge).

How it works

The system connects to Android devices via USB or WiFi (supporting QR code pairing for Android 11+). It uses an OpenAI-compatible LLM API to interpret user requests and translate them into on-screen actions. It offers two primary operational modes:

  • Classic Mode: A single vision model handles the entire loop of understanding, planning, and executing.
  • Layered Agent Mode: A two-tier architecture where a "Planning Layer" handles high-level reasoning and task decomposition, while an "Execution Layer" focuses on the actual screen observation and interaction.

It integrates scrcpy for low-latency screen mirroring and manual control, and includes a Cron-style scheduler for 24/7 automation when deployed via Docker.

Who it’s for

  • General Users: People wanting an AI assistant to handle repetitive mobile tasks (e.g., ordering food, checking prices).
  • Developers/QA Engineers: Those needing AI-powered UI automation for app testing and regression tests.
  • Power Users: Individuals running home servers (NAS/VPS) who want to automate mobile apps 24/7.

Highlights

  • Scheduled Tasks: Built-in Cron system for automated daily check-ins or periodic monitoring.
  • Multi-Device Management: Control several Android devices simultaneously with isolated states.
  • MCP Protocol Support: Built-in Model Context Protocol server allowing integration with AI apps like Claude Desktop and Cursor.
  • Workflow Management: Save frequent complex tasks as reusable workflows for one-click execution.
  • Docker Deployment: Supports x64/ARM64 architectures for stable, server-side 24/7 operation.
  • Wireless Pairing: QR code-based pairing for Android 11+ devices, eliminating the need for cables.

Related

  • Project
    xinzezhu/Open-AutoGLM-Android

    An AI-powered smartphone automation assistant that uses vision language models to execute natural language commands on Android via accessibility services.

  • Project
    Significant-Gravitas/AutoGPT

    AutoGPT is an open‑source platform for building, deploying, and managing autonomous AI agents. Users can describe a goal in plain English or assemble a workflow visually; the system creates an LLM‑driven agent that interacts with 45+ integrations (Gmail, Slack, GitHub, etc.) to complete tasks such as drafting reports, triaging incidents, or generating marketing copy. The project offers a paid hosted service and a free self‑hostable Docker appliance, with the core platform under a Polyform Shield license and the classic agent code under MIT.

  • Project
    acon96/home-llm

    A privacy-focused integration for Home Assistant that enables local LLM-powered voice and chat control of smart home devices using specialized small language models.

  • Project
    yashab-cyber/opendroid

    An autonomous AI agent for Android that plans and executes multi-step tasks across various apps using UI automation and a wide range of LLM providers.

  • Project
    Core-Mate/OpenGUI

    OpenGUI is a framework that lets AI agents control real Android phones by interpreting screenshots and issuing UI actions. It provides WorkBuddy and DeepSeek Harness plugins for easy chat‑based use, a full optional backend for advanced task planning, and a small Android client that performs taps, swipes, typing, etc. Ideal for AI‑driven testing, automation, and content creation on mobile devices.