Shiplight alternative: Retracio
Shiplight is an agent that walks your app in a real browser and writes tests as plain YAML in your repository under tests/; the YAML runs through the Shiplight CLI, on Shiplight-hosted CI runners, or in your own CI, and can be transpiled to standard Playwright files (checked 2026-09-08). Retracio is a desktop app. A tester walks through the scenario by hand, marks what should be true on each screen, and the app writes a Playwright spec into the local checkout, reusing the page objects, fixtures, and locator style already there, with no vendor import, plugin, or runtime.
| Criterion | Retracio | ShiplightAI test generator |
|---|---|---|
| Follows the conventions of your repository | Yes | reads existing specs and tests before creating; writes tests in Shiplight YAML format under tests/ |
| Where tests run | Local or cloud | both |
| Who owns the test code | Plain test files in your repository | both |
| Works offline | ||
| Maintenance model | Edit the test like any other file | self-healing |
| Output frameworks | Playwright | playwright |
Alternatives checked on 2026-09-08 against their own websites and documentation. Empty cell: not confirmed.
Shiplight fits when…
- You want an agent to explore the application on its own and produce the suite, kept as plain YAML you can read and change (checked 2026-09-08).
- Your pipeline can run tests through the Shiplight CLI or on Shiplight-hosted runners, and a self-healing cache that repairs a locator during a run without rewriting the YAML matches how you handle UI drift (checked 2026-09-08).
- A Playwright suite already exists and you want an agent-maintained suite running alongside it, with ejection to Playwright files as an option for later (checked 2026-09-08).
Retracio fits when…
- The E2E suite is Playwright in the repository, and every new spec has to pass the same review, lint, and formatter config as the ones written by hand.
- Testers already run scenarios manually and want each run to end with a committed spec whose assertions match the checks they marked, placed next to similar tests and using the same helpers.
- Security review requires that source code, cookies, and credentials stay on the machine and that the model is called through an API key the company controls.
Questions
What is an AI testing agent?
An AI testing agent is software that operates the application itself, decides which paths to cover, and writes the tests. Shiplight describes its product this way: agents walk your app in a real browser and write tests in plain language you can read and change (checked 2026-09-08). Retracio divides the work differently. The person performs the scenario and marks the expected outcomes; the app records the steps, resolves each element to a stable locator, and turns the run into a Playwright spec that matches the repository.
Who owns the test code with Shiplight and with Retracio?
With Shiplight, tests are plain YAML stored in your repo. They run directly with the Shiplight CLI, or you can transpile them to standard Playwright test files with no runtime dependency, and the documentation states you can eject at any time (checked 2026-09-08). With Retracio, the output is a Playwright spec from the start, written into the folder you choose in your local checkout, with no product import, plugin, or runtime. Uninstall the app and every generated test keeps working in your CI.
Do the generated tests follow our coding standards?
Shiplight's documentation says that on an existing project the agent reads your specs and tests first, and the tests it creates are written in Shiplight's YAML format under tests/ (checked 2026-09-08). Retracio writes in the language your suite already uses. It builds a conventions profile from the existing tests (folder structure, naming, fixtures, page objects, assertion style, lint and formatter config) and produces a spec that imports the page objects already in the repo instead of duplicating selectors inline. The result goes through code review like a file a teammate wrote.
Do the generated tests break when the UI changes?
Shiplight handles this with self-healing during a run: the healed locator is kept in a cache, the YAML in your repository is not rewritten, and the file changes only when your coding agent commits an update (checked 2026-09-08). Retracio works on the file itself. Each element the tester touched is resolved to a role, label, or test-id locator, following the repo's own convention such as a data-testid prefix. When a step fails on review, the app regenerates that one step and leaves the rest of the file, including your edits, untouched.
How do the generated tests integrate with CI/CD?
Shiplight tests run locally with a single command, on Shiplight-hosted CI runners, or in your own CI, and the YAML transpiles to a standard Playwright test at run time (checked 2026-09-08). Retracio takes no part in the pipeline. The spec it writes is ordinary Playwright, so the job that already runs your suite picks it up without configuration changes. If the repository has no E2E job yet, the app offers a ready job snippet for GitHub Actions or GitLab CI; Jenkins, Azure Pipelines, and CircleCI are planned.
Does my source code leave my machine?
No. The browser, the recording, the repository scan, and the test execution happen inside the desktop app on your computer. What goes out is the recorded steps, trimmed DOM snapshots, and excerpts of the conventions profile, sent to Anthropic Claude through an API key you provide. Source code, generated tests, cookies, screenshots, and credentials stay local, and the app never clones or uploads the repository. Shiplight's local setup also runs on a Google or Anthropic API key, and local authoring needs no Shiplight account (checked 2026-09-08).