droid-ash/finalrun-agent

AI QA Agent for mobile apps

What it solves

FinalRun simplifies mobile app testing for Android and iOS by replacing complex scripting with natural language. It eliminates the need to manually write brittle test scripts by allowing developers to define tests in plain English and using AI to execute them on emulators or simulators.

How it works

Users write test specifications in YAML using plain English. The tool then launches the app on a mobile device and uses a multimodal AI model (such as Gemini, GPT, or Claude) to "see" the screen and perform actions like tapping, swiping, and typing. It produces a pass/fail report complete with video recordings and device logs. Additionally, it provides "skills" for AI coding agents to automatically generate tests from source code, run them, and enter a loop of diagnosing and fixing failures.

Who it’s for

Mobile app developers and QA engineers who want to automate end-to-end testing for Android and iOS apps without writing traditional test code.

Highlights

  • Natural Language Testing: Write tests in plain English via YAML files.
  • Multimodal AI Execution: Uses AI models to visually interpret the app UI and interact with it.
  • Agentic Workflow: Includes skills for AI agents to generate tests from source code and automatically fix failing tests.
  • Cross-Platform: Supports both Android and iOS (local or cloud).
  • Comprehensive Reporting: Generates pass/fail reports with accompanying video and logs.

Related

  • Project
    droidrun/mobilerun

    An open-source framework that enables LLM agents to control Android and iOS devices using natural language, providing tools for UI inspection and device interaction.

  • Project
    block/trailblaze

    A natural-language device control system that lets AI coding agents drive iOS, Android, and web apps to create deterministic, self-healing regression tests.

  • Project
    minitap-ai/mobile-use

    An open-source AI agent that automates Android and iOS devices using natural language to perform tasks and scrape data from apps.

  • Project
    chenjigang4167/testhub_platform

    TestHub is an open‑source, AI‑enhanced test‑management system built with Django (backend) and Vue 3 (frontend). It covers requirement analysis, test‑case creation & review, API testing, web‑UI automation (Selenium/Playwright), Android automation (Airtest), performance testing (Locust), and a data‑factory toolbox. AI models (OpenAI, Anthropic, Gemini, etc.) can auto‑generate cases and drive browsers via a “smart mode”. The stack uses MySQL, Redis, Celery, Channels, JWT auth, and Allure reporting. The README provides full install steps, Docker support, and contribution guidelines.

  • Project
    lycorp-jp/sim-use

    A cross-platform CLI that enables AI agents to observe and interact with iOS and Android screens using token-efficient accessibility outlines and simplified action commands.