sean-a-ward unhooks Mike from a single AI vendor

The fork can now point its AI engine at whatever provider you choose - and let each user pick their own.

infrastructureintegration

Out of the box, Mike talks to one AI vendor and one only. sean-a-ward rewired that, so the fork can route its requests to any compatible provider - including marketplaces like OpenRouter, which act as a single doorway to dozens of competing AI models. A behind-the-scenes mapping layer translates Mike's built-in model names into whatever each provider expects, so nothing downstream has to change.

The choice isn't just an admin switch, either. sean-a-ward pushed it down to the individual: a new section under account settings lets each user supply their own provider details and model mapping. There's also a careful fallback so deployments that haven't yet updated their database keep working rather than breaking on the spot.

So what Anyone running Mike who wants to control cost, data residency, or vendor lock-in now has a real lever instead of a single take-it-or-leave-it AI supplier.

View this fork on GitHub →

Spotted something wrong? Or know the PR text has fresher detail than the writeup above?

Commits in this thread

3 commits from sean-a-ward/mike, oldest first. Source extracted verbatim from the harvested git log.

SHA Subject Author Date
800b5b39 feat(llm): support OpenAI-compatible endpoints Sean Ward 2026-05-20 ↗ GitHub
ae68cee5 feat(settings): configure OpenAI-compatible endpoints Sean Ward 2026-05-20 ↗ GitHub
9573a579 fix(settings): tolerate pending OpenAI config migration Sean Ward 2026-05-20 ↗ GitHub

Capture this thread into my fork

Download a single Markdown prompt that tells Claude how to port every commit above into your working tree — adapting paths and structure to match your repo. Run it via claude -p < capture-thread-513.md from inside the repo you want the changes in.

⬇ Download capture-thread-513.md