The runtime platform for cloud agents

Revyl gives your agents a runtime to run and verify software in. An agent runs your app in a cloud session, such as a Web browser (alpha) or a mobile simulator, and Revyl records what happened. What it observes goes into Atlas: a record of how your app behaves that your company owns and any person or agent on your team can query.

Start from where you work

GitHub

Get a verdict from a live session on every pull request

Coding agent

Let Cursor, Claude Code, Codex, or another agent drive your app

CLI

Start sessions, check what your app does, and query Atlas from your terminal

Dashboard

Open Atlas, sessions, and reports in the browser

How it works

Every change goes through the same loop. Each step is something you can open in Revyl.

Intent. A pull request, a prompt to your coding agent, or the plain-English steps of a test.
Agent execution. Your coding agent or the Revyl agent runs the app in a cloud session: a proof run, a test run, or a dev loop.
Runtime evidence. Each run leaves a report with video, screenshots, logs, and network traffic.
Verified behavior. Validation steps and the proof verdict record whether the app did what was intended.
Stored behavior. Atlas adds the screens, pages, and transitions the run observed to your app's record.
Questions. People open Atlas in the dashboard. Agents query it with revyl atlas and the Atlas skill.
New intent. What you learn, such as a screen no test covers, becomes the next change, test, or exploration.