A new parallel backend bolts on around 90 Australian court and tribunal databases plus a privacy-law compliance checker, alongside a pivot to Microsoft's cloud.
ExigoTech-Beno/mikeoss
An Azure-native rebuild of Mike aimed squarely at Australian legal practice, with AustLII case law wired in from the start.
This fork from ExigoTech-Beno reimagines Mike as an Azure-first product for the Australian legal market. Instead of running on the upstream stack, it leans into Microsoft's AI Foundry ecosystem and pairs that with plugins for Australian legal sources like AustLII.
The direction is opinionated: a single large drop establishes a parallel backend service intended to take over from upstream's, built around hosted Azure agents and Semantic Kernel. Read alongside the AustLII focus, this looks less like a general experiment and more like the early scaffolding of a jurisdiction-specific deployment.
It's very early - one substantial commit's worth of work - so a lot is still implied rather than shipped. Curious readers should click through to GitHub to see how far the Azure-native bet has been carried.
What's in it
- Azure AI Foundry backend A parallel Python service designed to replace the upstream backend with a hosted Azure agent, built on Semantic Kernel.
- Australian legal grounding Plugins that pull from AustLII and other Australian legal sources, pointing at use inside Australian practice.
- Microsoft-stack opinionation The architecture commits to the Azure ecosystem end-to-end rather than staying cloud-neutral.
Direction
infrastructureintegration
Activity
Threads of work (detailed view)
ExigoTech-Beno teaches Mike to read Australian case law
A new parallel backend bolts on around 90 Australian court and tribunal databases plus a privacy-law compliance checker, alongside a pivot to Microsoft's cloud.