Kane CLI (TestMu AI)

AI Development Tools

Browser testing in plain English for devs and AI agents.

Kane CLI (TestMu AI) screenshot

What does Kane CLI (TestMu AI) do?

Kane CLI is a terminal-native browser testing tool built for developers, QA engineers, and AI coding agents. Describe a browser flow in plain English and Kane CLI executes it in a real Chrome browser, verifies every step, and returns a clean pass or fail. No selectors to write, no test scripts to maintain, no framework to learn from scratch.

The tool is built for two audiences simultaneously. For developers and QA engineers, it provides a fast verification loop before opening a PR, before a deploy, or before a QA handoff. For AI coding agents like Claude Code, Codex CLI, and Gemini CLI, it is a browser verification primitive that agents call when they need to confirm that what they built actually works in a real browser end to end.

Kane CLI ships with three execution modes. Interactive TUI keeps the browser open between runs so session state carries over, useful for development and exploratory testing. Headless CLI runs flows with no visible browser and produces a deterministic exit code for shell scripts and CI/CD pipelines. Agent mode outputs structured NDJSON line by line, purpose-built for AI coding agents to consume and act on programmatically.

The automation engine is vision-based rather than selector-based. It identifies elements by what they look like on screen, not by CSS classes or DOM position, making it resilient to UI changes that break traditional automation tools. Built-in autoheal and smart waiting handle loaders, animations, shadow DOM, and dynamically rendered components.

Setting up an AI coding agent to use Kane CLI takes one command: npx @testmuai/kane-cli-skill. This installs a skill file that tells Claude Code, Codex CLI, or Gemini CLI exactly how to call Kane CLI and interpret its structured output.

Test.md is Kane CLI's agent-native test format. Any session can be captured as replayable markdown that is human-readable, version-controllable, and executable by AI agents. Flows can also be exported to native Playwright scripts or imported from existing Playwright and Selenium suites.

Every run generates a shareable evidence link with session recording, step-by-step logs, and full network capture, synced automatically to the KaneAI Test Manager dashboard.

Free tier: 200 credits per month. Paid plans from 19 dollars per month. Available on macOS, Linux, and Windows.

Last modified
Jul 23, 2026
Date listed
Jul 23, 2026