Mobilerun

Mobilerun is an open-source AI agent framework that controls iOS and Android devices through natural language commands.

Mobilerun is an open-source framework for AI agents that control iOS and Android devices. It works with any large language model, allowing users to swap providers in one line. The platform offers task agents for multi-app automation, testing agents for writing mobile tests in plain English, and research agents for data extraction. Key capabilities include vision mode, reasoning mode, structured output with Pydantic models, custom tools, and pre-built app cards. Users can run the framework locally or scale to the managed cloud with hosted devices and parallel agents.

Mobilerun at a glance

Best for: Software engineer
Runs on: Web, iOS, Android
Pricing: Free $0/month; Developer $20/month; Startup $99/month; Scaleup $299/month; Enterprise custom pricing
Released: April 2025
Category: AI agent tool
Website: mobilerun.ai

Key features

LLM-agnostic framework with one-line provider swapping
Vision mode with screenshot-based fallback
Reasoning mode for multi-step planning
Structured output with Pydantic models
Custom tools registration
Pre-built app cards for popular applications
Local execution and managed cloud scaling

Use it for

Automate complex multi-app tasks using natural language
Write mobile tests in plain English
Extract structured data from mobile applications

Alternatives to Mobilerun

Mobile-Agent — Automates cross-platform GUI tasks via planning and multimodal memory.
agent-device — Token-efficient snapshots and semantic references for native mobile and TV apps.
PhoneClaw — It executes AI agent tasks and system tool calls entirely on-device.
Agent Squad — Runs multi-agent orchestration in Python, TypeScript, and locally on Apple devices.
OpenGUI — Automates real Android apps using an open-source AI mobile operator.
Mobile MCP — Connects AI agents directly to real mobile devices for automated testing and tasks.
AgentDock — It coordinates multi-device workflows and provides secure environment access.
MyAgent — It features built-in permission controls, long-term memory, and skill self-evolution.
OmniAgent — It evolves skills in real-time and dynamically hardens security during task execution.
Composio — Equips AI agents with tools, managed user auth, and sandboxes across 1,500+ apps
OpenDroid — Executes complex multi-step mobile tasks automatically using local or remote LLMs.
TestMu AI — Autonomous AI agents and cloud execution deliver 70 percent faster test runs.

All Mobilerun alternatives