See what agents can do on an iPhone.
Read the feed
See the app a user sees. Ranked, personalized, served by the app itself. No scraping, no public API, just the real in-app experience.
Explore social app workflowsWrite back
Act on any app, not just read from it. Post, reply, DM, react, follow. Your agent shows up the way a person does, because it is one.
See mobile QA testingWork across apps
Nothing gets done in one app. Your agent takes a screenshot in one, posts it on another, and shares it with the team in a third. The same thing you would do, you just don't have to do it anymore.
See account operationsUse the iPhone like it's an API.
Apps are the phone's native interface.
Now your agents can use them the way you would, enabling the work no API ever could.
Your BRIDGE between AI and the iPhone
- Take a screenshot and look at it
- Sends gestures like tap and swipe
- Open any app you have downloaded
- Navigates popups, permissions, notifications
- Verify the device with your passcode
Anything you can do on your phone,
your agent can do too.
Downloads new apps
Your agent can see what apps are on the phone. If it needs to do something and the app isn't there, it can download a new one from the App Store.
Texts with iMessage
Your agent can use the Messages app directly, or send quick iMessages when a workflow needs a fast reply.
Handles 2FA and verification
Push prompts, SMS codes, device checks, captchas. Your agent clears them and keeps going.
Uses your iCloud
Your agent can work from the same files, photos, and documents you already keep in iCloud, so it has the context it needs without a new handoff.
Pays for stuff you need
Your agent pays when it needs to, using everyone's favorite payment method: Apple Pay.
Locks and unlocks
Your agent unlocks the phone when there's work to do, and locks it when the work is done.
That is the idea behind TapKit: a real iPhone your AI can see, tap, type on, and use across apps. Learn what an iPhone agent is.
Use TapKit with your favorite agent.
TapKit plugs into the tools your agent already uses.
Run it from Claude, Codex, Cursor, OpenCode, or any MCP-compatible client, then give that agent a real iPhone it can see, tap, type on, and use across apps.
Simple setup. Serious work.
Get set up
Download the Mac app, configure your iPhone, and connect the two together.
Connect your AI
Use TapKit from Claude, Codex, or any other MCP client that can call tools.
Execute your first task
Tell your agent what to do. It uses your iPhone the way you would. Watch it work, or walk away. It'll keep going.
Frequently asked questions
How does TapKit work?
TapKit gives you programmatic control of real, physical iPhones through Apple's accessibility features. You send actions (tap, swipe, type) via our API, and they execute on your iPhone. For framework differences, compare TapKit with Appium.
Is this the same as an iOS simulator?
No. Simulators run virtual iOS environments that can't install or use apps. TapKit runs on real iPhones. See the full TapKit vs iOS simulator comparison.
What apps can TapKit use?
Anything on the App Store you can use.
How do I connect my AI agent?
Use our MCP server to connect directly to Claude Code or Cursor, our REST API with a Python SDK for custom integrations, or our Mac and Web apps for no-code control. The typical agent loop is: screenshot → send to your vision model → get action → execute on device. See how TapKit compares with iPhone Mirroring MCP.
Do I need my own iPhone?
Yes, TapKit is bring-your-own-device. You connect your own iPhone to your Mac and TapKit turns it into an API. We're exploring hosted phone options for teams that don't want to manage their own hardware. If you're evaluating hosted hardware, compare TapKit with device farms.
What does it cost?
TapKit starts at $100/month per phone with volume discounts for larger fleets. Get in touch for custom enterprise pricing.
Flat pricing. No surprises.
Unlimited usage for teams starting with one phone.
- Use it with any agent
- Unlimited team members
- Remote phone control
- Start with one phone. Scale whenever.
- Priority support
Volume pricing for large teams.
Running more devices, custom workflows, or production support? We will help your team scale the setup and keep it running.