e2e: AI app tests that replay a checked step with zero model calls

e2e is an open-source AI testing framework from TesterArmy for web, iOS and Android, with the same test API on all three. You describe a goal in plain language, an agent drives the app, and a normal assertion checks the result. Once a check passes after an agent step, e2e saves those actions, and the next run replays them with zero model calls until the app changes. Here is how I would set up a first test you can trust: pick your platform, give it one harmless goal, and add the check before you rely on the replay.