awizemann/harness — AI-driven user testing for iOS Simulator, macOS apps, and web apps.

Description and use

Harness is an open‑source dev‑tool that lets you define a plain‑language goal and then uses a large‑language‑model agent to automatically drive the UI of iOS simulators, macOS 14+ apps, and web applications, reporting any points of friction it encounters. It combines AI/ML with Swift 6 to provide automated user‑testing and UI‑validation across Apple platforms and browsers, helping developers catch usability issues early in the development cycle.

Problem

awizemann/harness helps add AI capability without starting from a blank model stack.

Outcome

Early or unclear: treat as research material until maintenance, releases, docs, and issue activity are verified.

Workflow

• prototype AI features
• build RAG or agent workflows
• evaluate model tooling

Evidence

AI-driven user testing for iOS Simulator, macOS apps, and web apps. Write a goal in plain language; an LLM agent drives the UI and reports friction. macOS 14+, Swift 6.

Source