I could certainly see the appeal of this sort of idea. Once your engineering org gets to a certain size, you can end up spending an eye-watering amount of money on CI compute - spinning up runners and executing thousands of tests for every single commit of every single pull request. That cost could decrease by a lot if, for PRs at least, you could use the dev's local machine instead.
The three prerequisites in my mind would be, that the CI workflow runs inside a local cluster of VMs (to match a real CI environment), that the results of the CI run are still uploaded and published somewhere, and that it's only used for pull requests (whereas a real CI is still used for the main branch).
This tool fails the second test; it doesn't publish the test results or in any way associate them with the status check.
Also, a larger organization is one in which human error is more likely, so I would expect a tool that relies on individual engineers not to make mistakes to be less suitable there.
Yes, I know the particular tool linked in OP does not pass the prerequisites.