Android Automation Tool Based on Vision-Language Models
-
Updated
Jan 8, 2026 - Kotlin
Android Automation Tool Based on Vision-Language Models
AI-powered voice automation platform with text-to-speech and automated calling capabilities. Features 20+ realistic AI voices, real-time audio waveforms, and enterprise-grade phone integration. Built with React, Node.js, ElevenLabs, and Exotel.
用自然语言控制 Android 手机的 AI Agent —— 基于 UI 结构树解析实现快速精准操控,截图视觉理解作为辅助,支持接入任意大语言模型。
Turn your Android phone into an MCP (Model Context Protocol) server. AI agents and desktop scripts can call your phone for live data and actions over LAN.
⌚ My open-source Samsung Routines
Create AI agents on your phone that automate your daily tasks.
A production-grade, voice-controlled multi-agent AI backend that autonomously controls Android devices using natural language. Runs a full perceive-decide-act-verify loop via 9 specialized agents, LangGraph orchestration, OmniParser hybrid perception, and reactive hybrid planning on real Android hardware.
MCP Server for Famulor Voice Agent Platform - AI-powered phone calling and voice assistant management through ChatGPT, Claude, and other MCP-compatible clients
AI voice assistant that actually controls your Android phone - Open Source
Open Phone Agent Model & Framework — Unlocking the AI Phone for Everyone (fork)
🤖 Enable AI-powered phone calls and assistant management with the Famulor MCP server for seamless communication through compatible clients.
Add a description, image, and links to the phone-automation topic page so that developers can more easily learn about it.
To associate your repository with the phone-automation topic, visit your repo's landing page and select "manage topics."