A third AI provider lands alongside Claude and Gemini - but the real signal is in the rebrand: this fork is aimed at running entirely on your own hardware.
jellz77/mike
jellz77's fork of Mike adds on-prem LLM support via Ollama, opening the door to fully self-hosted deployments.
This fork extends Mike with a third LLM provider option: Ollama, the popular runtime for running open-weight models on your own hardware. Where stock Mike leans on hosted APIs from Anthropic and Google, this version plumbs a local alternative through the stack end-to-end, streaming responses and all.
jellz77 is the sole author so far, and the work is tightly scoped. There's no rebrand, no UI overhaul, no shift in the product's positioning - just a deliberate addition aimed at users who'd rather not send case material to a third-party API.
Direction-wise, the bet is clear: make Mike viable for firms and solo practitioners with strict data-residency or confidentiality requirements who can run a model locally. If you're evaluating Mike for an air-gapped or on-prem deployment, this is the fork to look at.
What's in it
- On-prem LLM via Ollama Adds Ollama as a first-class provider alongside Claude and Gemini, so you can point Mike at a locally-hosted model instead of a hosted API.
- Streaming responses from local models Local inference is wired into the same streaming chat experience as the hosted providers - no second-class treatment for the on-prem path.
- Self-hosted deployment story Makes a fully self-contained Mike deployment plausible for firms that can't or won't send client material to third-party LLM APIs.
Direction
infrastructureintegrationsecurity
Activity
Threads of work (detailed view)
jellz77 takes Mike fully on-prem with Ollama
A third AI provider lands alongside Claude and Gemini - but the real signal is in the rebrand: this fork is aimed at running entirely on your own hardware.