midscene shipped an update

Midscene, an open-source vision-driven UI automation tool with 14k GitHub stars, shipped an update in July 2026. The tool uses screenshot-based interaction and natural language to automate testing and tasks across platforms, bypassing fragile DOM or accessibility tree dependencies.

midscene AI-powered, vision-driven UI automation for every platform. About midscene Open-source, vision-driven UI testing — write tests in natural language, automate any platform. Most UI automation — including AI tools that read the DOM or the accessibility tree — depends on page structure. That structure is fragile and incomplete: selectors break on every refactor, elements without semantic markup icon-only buttons, custom controls, are invisible to it, native apps and cross-origin iframes are out of reach, and it cannot tell whether something actually looks right. Midscene works from the screenshot alone, and you describe each step in natural language: Midscene is built for UI testing first, but the same vision-driven engine handles any UI automation task. midscene is an open-source project written primarily in TypeScript, with 14k stars on GitHub. It was last updated in July 2026. midscene vs. the alternatives All 19 alternatives → /alternatives/midscene