willchen96 gives Mike a second AI engine and bolts down the defaults

More choice over which AI powers the platform, paired with a safer baseline for anyone installing it cold.

integrationsecurity

willchen96 added OpenAI - one of the largest commercial AI providers - as an option for the models that drive the application, so it no longer leans on a single vendor for its language smarts. In the same pass, the project shipped tighter security settings in the version that comes straight out of the box, before anyone changes a thing.

The two moves fit together. Giving the software more ways to reach outside AI also gives it more surface to defend, and locking down the defaults keeps a fresh install from quietly trusting too much. It reads as a maintenance pass that makes Mike both more flexible about which AI it runs on and harder to misconfigure on day one.

So what If you run or are evaluating a legal product built on Mike, you get more freedom to pick your AI backend without inheriting a looser default setup.

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-644.md from inside the repo you want the changes in.

⬇ Download capture-thread-644.md