Let an AI model use a real iPhone with a $7 ESP32: AirPlay eyes, USB HID hands, any OpenAI-compatible vision model.
Why it matters now: To provide an alternative to traditional iPhone automation methods that require a Mac and Apple developer account
The ESP32 iPhone Agent is a project that enables an AI model to use a real iPhone with a $7 ESP32 board. It uses AirPlay screen mirroring and touches the phone through a tiny ESP32-S3 board that plugs into the phone’s USB port as a mouse and keyboard. Any OpenAI-compatible vision model can be the brain, either a cloud API or a model run locally. The project does not require a Mac, Xcode, a signed helper app, or an Apple developer account, making it a unique solution for iPhone automation.
An ESP32-S3 board and a Linux or Mac computer