Plain Text Testing

All test tasks are plain Markdown files — no scripting required. Write automation in plain language. Manage Test Tasks

Minimal Token Usage

Handles complex scenarios and large chained test suites without hitting token limits. Real-world tests average as little as $0.15 per test case. AI Benchmark

Fully Harnessed

The agent is isolated through multiple layers of permission controls, from the container down to individual tools. Agent Permissions

AI Agnostic

Supports all major AI providers: Claude, OpenAI, Google Gemini, and DeepSeek. Provider Guide

Easy to Use

Delivered as a Docker image. Configure once and integrate seamlessly into your development, CI/CD, or QA pipeline. Waterwheel Docker Page