Agent-driven · iOS · Android · Web

Your agent flies the app.
You stay in the cockpit.

PilotStack gives a coding agent eyes and hands on iOS, Android, and web — all at once. It reads cheap semantic context (not expensive screenshots), understands Flutter at the widget level, and asks before it acts.

PilotStack cockpit manualco-pilotauto-pilot
iOS
390×844
Android
390×844
Web
390×844
drag(card, → 240,510)
Approve Deny

Built for agents that build apps

Drive every platform, side by side

iOS, Android, and web at once — tap, type, drag, pinch/zoom, scroll, rotate, scale text. One action, fanned across all three with run_on_all.

Cheap context, not screenshots

Agents read compact UI trees and one-line layout facts ("Column overflows bottom by 12px at 360×640") instead of burning tokens on images.

Deep Flutter understanding

Reads the Dart VM Service: widget tree, constraints, render sizes, and overflow — so Claude knows WHY a Flutter UI looks wrong. Zero app changes.

You stay in the cockpit

Watch live device frames and approve or deny each action like an IDE. Manual, co-pilot, or auto-pilot — your call, per session.

Runs locally, bills tiny

Simulators and emulators run on your machine for free. The cloud only meters usage, so per-action pricing stays in fractions of a cent.

An MCP server

Works with Claude Code or any MCP client. One command to register, and your agent can see and drive all platforms.

Three steps to a co-pilot

1

Install the daemon

pnpm build, then register the MCP server with one command.

2

Boot your apps

Web, an Android emulator, an iOS sim — attach a running Flutter app for deep context.

3

Let the agent fly

Claude drives all three side by side; you approve from the cockpit.

Stop guessing why the UI looks wrong.

Give your agent real eyes and hands across every platform — and keep your finger on the controls.

Read the quickstart