Tapkit launches: a Mac app that lets AI agents see, tap and type on real iPhones
edgarpavlovsky · x · 2026-09-29
Tapkit is a new Mac app that gives AI agents programmatic control of real iPhones — agents can see the screen, tap, swipe and type, turning every App Store app into an agent tool.
Key details:
- Works with any agent; can control multiple iPhones simultaneously
- Handles app installs, iMessage, 2FA/verification codes, iCloud, payments, locking/unlocking
- Runs on real devices, unlike iOS simulators which can't install or use apps
- Integrations: an MCP server for Claude Code and Cursor, a REST API with Python SDK, plus no-code Mac/Web apps
- Typical agent loop: screenshot → vision model → action → execute on device
The author suggests using posting APIs when an endpoint covers the whole job, and Tapkit when an agent needs the actual mobile app across drafts, notifications, account switching and cross-app steps.
More from coding & agent
- Ex-Google DeepMind engineering lead launches Fo, a personal AI that employs humans to finish tasks — Scobleizer · 2026-09-29
- Refero turns 2,000+ real design systems into DESIGN.md files so coding agents stop making ugly UI — victor_explore · 2026-09-29
- One creator and AI agents made a cyberpunk fashion film in 19 hours with ~50 prompts — full blueprint public — adrianscottcom · 2026-09-29
- VoidZero at Cloudflare, 4 months in: 80+ releases, Vite+ 1.0, Oxc 10x faster React builds — ritakozlov · 2026-09-29
- Prime Intellect brings multi-agent training to its open RL stack PRIME-RL — willcb · 2026-09-29
- Tracking Codex Subs Across Accounts: Switching by Reset Time to Max Out Capacity — idanbeck · 2026-09-29