Open-source macOS app: describe a test in plain language, an AI agent drives real iOS simulators (or your iPhone) and hands back an evidence-backed verdict — while you watch live.

Hey Product Hunt 👋 I built testcat because mobile UI testing is still either brittle scripts you babysit forever, or manual tapping before every release. testcat lets you describe a test in plain language and hands it to an AI agent that drives real iOS simulators — booting devices, tapping, typing, verifying — while you watch the whole thing live. At the end you get a verdict backed by actual actions and observations, not a hopeful "looks good." A few things I cared about: • Bring your own agent — Claude Code, Codex, opencode, or fully-local Ollama. • Trust by default — a completion gate cross-examines every success claim. No executed actions, no pass. • Local-first — everything persists to a local SQLite dashboard; nothing leaves your Mac. • Real devices too — it signs and installs an XCUITest runner so the same agent can drive your physical iPhone. It's open source (MIT) and macOS/Apple Silicon. Would love your feedback — especially on the agent profiles and the evidence/verdict model.

How does it actually handle flaky tests or simulator states between runs, and is there any way to step in manually if the AI agent starts going off-script mid-test?

@sibelkdrw4ar Good question — this is exactly what agent profiles are for. Each profile has an editable system prompt and a skills list, so you can give the agent explicit directives: recovery rules for flaky states, hard boundaries ("never touch account settings"), or step-by-step house procedures via a custom skill — and it loads them on every run. You can also stop a run at any moment while watching its reasoning live. More advanced mid-run controls (like steering a running agent) are planned.

Thanks for asking!

How does it actually handle flaky tests or simulator states between runs, and is there any way to step in manually if the AI agent starts going off-script mid-test?

Thanks for asking!

testcat

AI agents test your iOS app while you watch live

AI agents test your iOS app while you watch live