Created by

Close the loop with Argent

An agentic toolkit to control, debug, and profile iOS and Android applications. Your agent can navigate your app, explore the component tree, inspect network requests, and trace performance problems in your mobile apps.

npx @swmansion/argent init

Run this command to install Argent.

Works with

Let your agent take it from here

Now agents can run your iOS or Android app, see what happened, and keep going in the same session. Designed for AI agents, with a focus on speed and effective use of context.

Make it work

Simulator control & interactions

Launches an app, taps, swipes, types into fields, and navigates using coordinates from accessibility trees. It opens deep links and runs multi-step interaction sequences in a single call to move fast without round-trips. Argent provides feedback after every interaction, so the agent always knows what's happening on screen.

Make it right

Debugging

Find and fix issues faster by giving your agent the tools it needs. Argent can attach the debugger, explore the view hierarchy, read console logs, evaluate expressions, and inspect the React component tree at runtime. Also, it reads network requests, and HTTP payloads at both the JavaScript fetch and native network layer.

Make it fast

Profiling & optimization

Pinpoint and resolve performance bottlenecks by recording both React and native iOS profiles simultaneously and tracing slow React commits down to the native stack frame causing them. It detects UI hangs, render cascades, and memory leaks. Re-query the same profiling session for multiple issues without running it again.

FAQ

Argent is a toolkit for AI agents to control, debug, and profile iOS, Android, and React Native apps autonomously. At its core, it's a set of skills and an MCP server that connect AI harnesses directly to the iOS Simulator and Android emulator.

You'll need macOS, Xcode, and Node.js 18+. Run npx @swmansion/argent init in your project root and the installation wizard handles the rest. You can install Argent globally, which we recommend, or locally in a project.

Yes. Argent supports both iOS Simulators and Android emulators, so your agent can control, debug, and profile apps on either platform.

Argent works with Claude Code, Cursor, GitHub Copilot, OpenAI Codex, Google Gemini, OpenCode, Devin, Zed and any agent that can run shell commands.

Argent is free to use and published on npm as @swmansion/argent.

Speed and depth. Other tools usually rely on XCUITest, which has to switch between the test runner and the app for every interaction, slowing things down. Argent talks to the simulator directly, so your agent can interact with your app without waiting. Also, other tools usually focus only on controlling the simulator. Argent offers a full suite of diagnostic tools. Your agent can reproduce the problem, diagnose its root cause and fix it - all within a single session.

Argent uses a mixed licensing model. The source code is released under the Apache License 2.0 with proprietary binaries licensed solely for use within this project. See the full LICENSE here.

Argent helps you build
better apps, faster with...