Phantom · Flask
The same provider-compatible fake AI API, served by Flask over the Python port of phantom-core.
The point was not to have a Flask app. It was to find out whether phantom-core was genuinely framework-agnostic or merely untested outside one runtime. Building the same API on Flask, and then again on Django, is what turns that from an assumption into evidence — anything needing a per-framework special case would have been a design flaw in the library. Nothing did. Its test suite asserts the JSON it returns is byte-identical to the TypeScript deployment's, so the HTTP layer is held to the contract too, not just the shared library.
It consumes phantom-core, lab-languages — machinery that already existed, which is why this one took days rather than weeks.