ESP32 iPhone Agent
Lets a vision model use a real iPhone via AirPlay mirroring and a $7 ESP32 acting as USB mouse and keyboard.
Key features
- Mirrors the iPhone screen over AirPlay into JPEG frames
- Controls the phone with an ESP32-S3 USB mouse and keyboard
- Uses any OpenAI-compatible vision model, cloud or local
- Plans a goal, then taps, swipes, types, or draws
- Finds the pointer on screen and retries missed taps
- Category
- Agents
- Who it's for
- People who want an AI model to operate a real iPhone.
- Tags
- iphoneesp32visionllm-apibackground-jobsstoragemobile
- Website
- github.com
- Listed
- 2026-10-14
Frequently asked questions
Is ESP32 iPhone Agent free?
Yes. ESP32 iPhone Agent is open source and free to use.
What is ESP32 iPhone Agent used for?
Lets a vision model use a real iPhone via AirPlay mirroring and a $7 ESP32 acting as USB mouse and keyboard. Typical uses: mirrors the iPhone screen over AirPlay into JPEG frames; controls the phone with an ESP32-S3 USB mouse and keyboard; uses any OpenAI-compatible vision model, cloud or local.
What are the best ESP32 iPhone Agent alternatives?
Alternatives in the same category include Omnara, Mastra, Docker Agentic Platform, Agensh, Harness².
Related in Agents
See all →- Agensh Self-organized multi-agent harness. Agents claim sub-tasks and merge progress without a central orchestrator. MIT.
- Agentic Batch Changes Describe a change in plain language. The agent scopes it across your indexed codebase and tracks it through to merge.
- Agno Python framework for agents, formerly Phidata.
- Alter Privileged access for AI agents. Vaulted credentials, per-call policy, and an audit log. Free tier is 10,000 API calls a month.
- Amazon Bedrock AgentCore Serverless AgentCore Runtime in Amazon Bedrock for deploying and scaling AI agents.
- AutoGen Microsoft's framework for multi-agent conversations.
