manueljpconde teaches mikeEU to run on your own AI model

A new setting lets whoever runs the deployment point Mike at a self-hosted language model instead of a third-party cloud.

infrastructuresecurity

Most legal-AI tools send your documents off to someone else's servers to be processed. manueljpconde adds an alternative: the team behind a deployment can wire Mike up to a model running on their own hardware - using self-hosting tools like Ollama or LM Studio, which let you run AI models locally. Everything is configured on the server side. The address, the model, and the keys never reach the browser; users just see a new model they can pick.

There's an honest catch, and the fork is upfront about it. The heavier features - editing documents, generating Word files, running workflows, pulling tables out of files - depend on the model being able to use tools, and most local models can't do that reliably yet. So those are switched off by default unless you've tested your setup and turned them on.

So what Firms that can't let client files leave their own infrastructure now have a path to run Mike entirely in-house - with eyes open about which features still need a capable model.

View this fork on GitHub →

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

Commits in this thread

1 commit from manueljpconde/mikeEU, oldest first. Source extracted verbatim from the harvested git log.

SHA Subject Author Date
c0361944 feat: add self-hosted local llm provider Manuel Conde 2026-05-09 ↗ 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-255.md from inside the repo you want the changes in.

⬇ Download capture-thread-255.md