Ihandclaw — AI skill for Claude Code
Let AI agents drive a real iPhone: an ESP32-C3/C5 acts as a Bluetooth keyboard + mouse, an AirPlay mirror is the agent's eyes.
How to install Ihandclaw
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open pgodlews/ihandclaw and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Ihandclaw does
Let AI agents drive a real iPhone: an ESP32-C3/C5 acts as a Bluetooth keyboard + mouse, an AirPlay mirror is the agent's eyes. MCP + HTTP API, droidclaw/LM Studio support, and the Benchy benchmark for comparing models. Proof of concept.
Alternatives in AI
- CodeIsland — Real-time AI coding agent status panel in your MacBook notch — live status, approvals & replies for 13 AI tool 2.3k ★
- Cc Mirror — Create multiple isolated Claude Code variants with custom providers (Z.ai, MiniMax, OpenRouter, LiteLLM) 2.1k ★
- Agentboard — Web GUI for tmux optimized for AI agent TUIs, with support for iOS safari and mac w/ keyboard shortcuts 410 ★
README
ihandclaw
**Proof of concept.** Works end to end on one reference setup; expect rough edges.
ihandclaw (Python package `iphone_hand`) lets an AI agent operate a real iPhone through an ESP32 acting as a Bluetooth keyboard and mouse, while the agent sees screenshots from a mirrored screen. The host turns agent requests into HID actions and uses visual feedback to position the pointer. You can build the hardware, compare agents and models on the Benchy benchmark, experiment with fine-tuned models, and contribute playbooks that teach agents how to navigate iOS apps. The current reference phone is an iPhone XS running iOS 18; this is an experimental project, not a universal iOS automation system.
Claude (MCP / Claude Code) or droidclaw + LM Studio model
|
Python host / daemon HTTP API
| ^ screenshots / OCR
USB serial or TCP |
| UxPlay AirPlay (Linux / macOS)
ESP32-C3 or C5 or USB capture (macOS prototype)
| BLE HID |
+---------------> iPhone
Read: the [design contract](docs/SPEC.md) defines the protocol and point coordinates. The [frame-source guide](docs/frame-sources.md) compares AirPlay, USB, and developer services; the original Portal+/ADB path also remains available.
Why ihandclaw
Read: most iPhone automation (XCUITest, WebDriverAgent, Appium) needs a Mac with Xcode, a signed helper app on the phone and Developer Mode. ihandclaw drives the phone from the outside, the way a person with a keyboard and mouse would:
- No Mac. The host runs headless on Linux (the reference setup is a Linux mini PC); firmware bu
Related Skills
Hyper Hand
Let AI agents (Claude Code, Codex, any MCP client) control Hyper-V Windows VMs: screenshots, mouse, keyboard,
HyperHand
Let AI agents (Claude Code, Codex, any MCP client) control Hyper-V Windows VMs: screenshots, mouse, keyboard,
Hands
Cross-platform computer-use agent. Your LLM on your mouse, keyboard, and screen. Windows (PowerShell), macOS (
Wardlume
Lock your Mac keyboard & mouse, keep the screen visible — botsit your AI agents (Claude Code, Codex, Cursor) w
AgentLimb
Let any AI coding tool — Claude Code, Cursor, Codex — drive your real Chrome. One-prompt setup, muscle memory,
Clawbrowse
Let Claude Code drive your real, logged-in Chrome. MV3 extension + zero-dep MCP server, element-table percepti
Related Agents
Archetypes
Elevare Studio — Design Archetypes (which benchmark applies to THIS job)
Realtime Dev
Real-time - Socket.io, WebSocket, Pusher, MQTT/ESP32, WebRTC: room, stato server-authoritative, riconnessioni.
Unity Network Dev
Implements multiplayer networking — writes network scripts and uses MCP to set up NetworkManager, spawn points