Revyl

Easily create and control ios, android cloud simulators. As the bottleneck becomes more and more the review of code and verification, there is no better way to review than checking the true runtime behaviour of the software. We recently released our cli and session viewer which allows you to spin up simulators in seconds, and pragmatically control the devices to do arbitrary commands. All using only screenshots on a custom grounding model. In this video we create a ios simulator session using the UI, and attach to it in the CLI and send a command to tap "safari" and open the safari button on the phone. Companies are using the CLI and session viewer for many creative use cases already. - verify changes by letting claude/codex or another coding agent drive it - sending sessions links to teammates to allow them to see mobile preview developments. - using it for pixel diffing design review to figma

Agents can one shot mobile apps, but testing is still the bottleneck. So we built a CLI that gives Claude Code the one thing it was missing - eyes and hands The best part? t's fully vision-based: - No scripts, no selectors, no element IDs - It interacts with the app exactly like a human would Claude now writes code → tests it on the app → sees what broke → fixes it Spawn a cloud agent, go to sleep, and wake up knowing it actually worked.

As we see more and more long running tasks verification becomes the bottleneck. As evidenced by the launches today by Cursor and Devin Built a tool that runs your iOS and Android apps and creates replayable reports that can be run. The reports contain a full timeline - Description of all the stuff that happened - Performance information - Microservice tracing

having trouble using simulators across multiple worktrees and verifying your changes? built a tool that - starts an ios/android device in the cloud - hotreloads changes so you can view updates in real time Using it to run parallel worktrees and verify that the changes are correct. Don't let verification or compute be the bottleneck

Built a lightweight mobile SDK that lets our QA agent know exactly what's happening under the hood. It tracks: - CPU/memory performance - Network requests & failures - Screen transitions - Tap gestures - Full distributed traces Give an agent this level of context and it stops guessing why a new feature isn't working. It just reads the trace and fixes the code.