CaliLuke pulls Mike off the cloud and turns it into a private job-search workbench

This fork has stopped being a legal-AI tool entirely - it's being rebuilt as a single-user app that runs start-to-finish on your own machine.

infrastructureworkflow

CaliLuke has rebranded the fork "Luke" and given it a completely different job: a local-first workbench for running a job search, where each project is a position you're chasing. The bigger story is the engineering pivot underneath. The original cloud plumbing - hosted database, hosted auth, cloud file storage - is on its way out, replaced by tools that live entirely on your own computer: an embedded database that's just a file on disk, local file storage, and Ollama, which runs AI models on your laptop instead of sending anything to a remote service.

The team has published an eight-stage migration plan and landed the first piece - proving the local database can save data, close, reopen, and read it back reliably. The old backend stays alive only as a stopgap while the new one is built.

So what Worth a look for anyone interested in fully offline, no-cloud AI tools - though note this fork has left the legal domain behind.

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 CaliLuke/mike, oldest first. Source extracted verbatim from the harvested git log.

SHA Subject Author Date
9470452d Add Luke local-first migration plan and persistence spike CaliLuke 2026-05-06 ↗ GitHub
commit body
Reframes the repo as Luke (a local-first single-user job-search workbench),
adds the milestone plan for migrating off Supabase/Express to a Loom Go
backend on embedded SurrealDB, and lands the Rust FFI persistence spike
that the plan depends on.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

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-70.md from inside the repo you want the changes in.

⬇ Download capture-thread-70.md