A Mac app that lets AI agents control a real iPhone
The approval layer for AI agents
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
US
Pricing model
Paid
Freemium
Pricing
Monthly: $25/month for 1 iPhone. Lifetime: $99 once for 1 iPhone. Lifetime Plus: $199 once for up to 5 iPhones. All plans include access to Claude Code and Codex on your own subscription, run on your Mac with no cloud, and include all updates.
Open Source: free and self-hosted. Free: $0/month hosted plan with up to 5 members. Scale: $20 per user per month. Enterprise: Custom annual contract.
Key features
Control a real iPhone from your Mac over USB and Bluetooth
Connect Claude Code, Codex, Cursor, Hermes, OpenClaw and any MCP client
Built-in chat that runs on your own Claude or ChatGPT subscription
Use any App Store app and your own logged-in accounts
No installation on the iPhone, no developer mode needed
No Xcode, Apple Developer account or code signing required
Optional phone unlock with passcode stored in macOS Keychain
Local MCP server that only accepts connections from your Mac
Free trial for the first hour of live use
Works with up to 3 Macs per license
Tool call interception for all agent frameworks
Automatic approval rules to prevent fatigue
AI judge for complex rule evaluation
Works with LangGraph, CrewAI, Mastra, Claude Agent SDK and more
Open Agent Approval Protocol for framework independence
Self-hosted or cloud-hosted deployment options
Custom permission policies and organization controls
What makes it different
Real iPhone instead of simulator - runs your actual apps and accounts with no virtual copy limitations
Local-only operation with no account or cloud - your data stays on your Mac
No developer setup required - just plug in a USB cable and pair Bluetooth
Bring your own AI - works with agents and plans you already pay for
Pay once, keep it for life with no subscriptions required
Framework-agnostic: works with any AI agent through the open Agent Approval Protocol
No vendor lock-in: open source spec and SDKs let you swap providers without rewriting agents
Comprehensive audit trail for accountability and compliance
Meets reviewers where they work with multi-platform notifications
Policy-based routing to eliminate approval bottlenecks
Zeptap
withHuman