# iphone-use Open-source, self-hosted iPhone control for AI agents on macOS. - Findings24: - Website: - Pricing: Freemium - Categories: AI Agent Infrastructure, AI Browser Automation, Developer Tools ## What is iphone-use? iphone-use is an open-source tool for giving AI agents control of a physical iPhone. It exposes screen text and interaction primitives—including tapping, typing, and swiping—through a Rust-based, self-hosted system intended to run on macOS. The project is designed for agents that need to observe a mobile interface and perform actions on the device rather than interact only with a simulator or static test fixture. ## What can iphone-use do? ### Screen text and touch control Lets an agent work with visible iPhone content and perform core interactions such as tap, type, and swipe. ### Custom XCTest runner Includes a custom XCTest-based runner as part of the device-control stack for driving iPhone automation. ### Multiple control interfaces Provides a command-line interface, HTTP API, and MCP integration so an agent workflow can use the interface that best fits its runtime. ### Browser takeover Supports browser-oriented workflows in which an agent can take control of an existing mobile browsing session. ### Replayable flows Supports recording or defining repeatable interaction flows that can be run again instead of reconstructing every action manually. ### Rust and self-hosted operation The project is implemented in Rust and is positioned for local operation on macOS, keeping the control service in the operator’s environment. ## Use Cases ### Mobile UI agent workflows Build an agent that reads an iPhone screen, chooses an action, and executes taps, text entry, or swipes against a real device. ### Repeatable app flows Turn a multi-step interaction into a replayable flow for recurring checks, demonstrations, or internal automation. ### Browser session takeover Let an agent continue work in a browser session that is already open on the iPhone, rather than starting from an empty context. ### Tool integration for coding agents Expose phone actions through the CLI, HTTP API, or MCP so they can be connected to different agent runtimes and orchestration setups. ## Frequently Asked Questions ### What does iphone-use control? It is intended to control a real iPhone, with support for reading screen text and performing taps, typing, and swipes. ### How can an agent connect to it? The project provides a CLI, an HTTP API, and MCP integration as control and integration surfaces. ### Where does it run? The project describes itself as self-hosted on macOS. The supplied source does not provide a complete compatibility matrix for macOS or iPhone versions. ### Is iphone-use open source? The repository is public and lists an MIT license. The source does not establish a separate hosted pricing plan for iphone-use. ## Quick Facts - **Product type**: Open-source mobile automation and AI-agent control tool - **Primary device**: Real iPhone - **Host platform**: macOS - **Implementation**: Rust - **Agent interfaces**: CLI, HTTP API, and MCP - **License**: MIT