jpbreda tries to let Mike run on your own hardware

A proposal to point Mike at self-hosted AI models, not just the big commercial clouds.

integrationinfrastructure

Out of the box, Mike talks to hosted commercial models from Anthropic (Claude) and Google (Gemini). jpbreda proposed a third path: connecting Mike to local, self-hosted model instances running on infrastructure you control. The setup uses vLLM, a popular engine for serving open models, which speaks the same wire format as OpenAI - so one adapter can cover any endpoint that follows that standard.

The design was deliberate about who configures it. Whoever runs the server sets the endpoint and model names once, and the local option becomes available to every user - no one has to paste in their own API key. It appears as a new choice in the model picker alongside the existing providers, and the original Claude and Gemini paths keep working untouched. jpbreda reported testing the full flow, including document generation, against a live endpoint. Note: the proposal was closed without being merged, so it hasn't landed in the main project.

So what Worth a look for legal teams with data-residency rules or a mandate to keep matter data off third-party clouds.

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

Commits in this thread

3 commits from jpbreda/mike, oldest first. Source extracted verbatim from the harvested git log.

SHA	Subject	Author	Date
`0c84ef49`	feat: Add LocalLLM (vLLM) provider support	Joseph Breda	2026-05-02	↗ GitHub
commit body - Add OpenAI-compatible LLM provider for local vLLM endpoints - Support for configurable model names via environment variables - Add LocalLLM Main and LocalLLM Lite as default models - Update model selector to include LocalLLM options - Fix generate_docx title fallback for missing parameters - Add LibreOffice dependency note for document conversion
`cc951105`	feat: Replace unsloth model with placeholder in .env.example	Joseph Breda	2026-05-04	↗ GitHub
`fe3fd823`	docs: Add LLM configuration options to README	Joseph Breda	2026-05-04	↗ GitHub

SHA

Subject

Author

Date

0c84ef49

feat: Add LocalLLM (vLLM) provider support

Joseph Breda

2026-05-02

↗ GitHub

commit body

- Add OpenAI-compatible LLM provider for local vLLM endpoints
- Support for configurable model names via environment variables
- Add LocalLLM Main and LocalLLM Lite as default models
- Update model selector to include LocalLLM options
- Fix generate_docx title fallback for missing parameters
- Add LibreOffice dependency note for document conversion

cc951105

feat: Replace unsloth model with placeholder in .env.example

Joseph Breda

2026-05-04

↗ GitHub

fe3fd823

docs: Add LLM configuration options to README

Joseph Breda

2026-05-04

↗ 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-802.md from inside the repo you want the changes in.