willchen96 puts OpenAI in the driver's seat alongside Claude and Gemini

Mike now offers a third AI engine, and a cleaner story about who controls the keys.

integrationsecurity

Mike already let users pick between Claude and Gemini for its legal work. willchen96 has added OpenAI as a full third option, wired straight into the same model picker - so the choice of underlying engine is now a setting, not a rebuild. For firms wary of betting everything on a single AI vendor, that optionality is the headline.

The quieter change matters just as much. The settings screens were reworked so that when an administrator configures a provider's key at the server level, individual users can no longer overwrite it from the browser - server-side keys take precedence, full stop. The same release locks down the default database so the app's own tables can't be reached outside the backend's controlled path. Together it's a tidy step toward giving whoever runs the deployment real authority over credentials and data access.

So what Anyone weighing Mike for a firm should note the new vendor flexibility and the firmer admin grip on API keys and data.

View this fork on GitHub →

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

Commits in this thread

2 commits from willchen96/mike, oldest first. Source extracted verbatim from the harvested git log.

SHA Subject Author Date
bef75b08 feat: add OpenAI model support and harden OSS security defaults willchen96 2026-05-09 ↗ GitHub
f40c25d0 Merge pull request #48 from willchen96/sync/openai-model-support cosimoastrada 2026-05-09 ↗ GitHub
feat: add OpenAI model support and harden OSS security defaults

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-256.md from inside the repo you want the changes in.

⬇ Download capture-thread-256.md