Summary

FinalRun Agent is an AI-driven CLI tool for automated mobile app QA testing. It enables developers and QA engineers to create and execute tests using natural language YAML specifications, streamlining the testing process and accelerating feedback. The agent leverages LLMs to interpret test cases, interact with the app UI, and report results, reducing manual effort.

How It Works

The AI-powered CLI translates plain-English YAML test specifications into automated actions. It launches the target Android/iOS app on an emulator/simulator, then uses AI models (Gemini, GPT, Claude) to visually interpret the app's state and perform UI interactions like tapping and swiping. This allows dynamic test execution based on the app's current UI. Comprehensive reports include pass/fail status, video, and logs.

Quick Start & Requirements

• Install macOS/Linux: curl -fsSL https://raw.githubusercontent.com/final-run/finalrun-agent/main/scripts/install.sh | bash. Windows (PowerShell): irm https://raw.githubusercontent.com/final-run/finalrun-agent/main/scripts/install.ps1 | iex.
• Prerequisites: iOS local testing requires macOS (xcodebuild). Android testing works locally on Windows.
• Dependencies: Requires API keys for AI providers (Google, OpenAI, Anthropic).
• Links: Docs, Website.

Highlighted Details

• AI test generation (/finalrun-generate-test skill) reads app source code to infer structure and propose test plans.
• Automated test execution and validation (/finalrun-use-cli skill).
• End-to-end "generate -> run -> diagnose -> fix" loop (/finalrun-test-and-fix skill) for autonomous bug resolution.
• Bring Your Own Key (BYOK) model for AI provider integration, using user-configured API keys and incurring standard API billing.

Maintenance & Community

• Community engagement via Slack Community.
• Includes standard development files: CONTRIBUTING.md, CODE_OF_CONDUCT.md, SECURITY.md, CHANGELOG.md.

Licensing & Compatibility

• License type is not explicitly stated in the README.
• Commercial use or closed-source linking compatibility is not detailed.

Limitations & Caveats

• iOS local testing is restricted to macOS environments due to xcodebuild dependencies.
• Test execution incurs costs based on the user's chosen AI provider's API usage.