brauliogusmao lets Mike run on your own machine

A fourth AI engine option means the model can live entirely on local hardware - no cloud round-trip required.

infrastructuresecurity

Until now, Mike leaned on hosted AI services from the big providers, which means every question and document touches an outside server. brauliogusmao adds Ollama - a tool for running open-source language models locally - as an alternative. Point Mike at a model on your own machine and nothing has to leave the building.

There's a clever accommodation here. Smaller local models are unreliable when asked to fetch documents on their own mid-conversation, so the work loads the relevant document text up front, before the model starts reasoning. That trades a bit of flexibility for far more dependable answers on modest hardware. The whole thing is bolted on as an extra layer, so firms that don't want it are unaffected. One caveat worth checking on GitHub: the backend exposes local models, but whether the interface fully surfaces them in a picker isn't yet confirmed.

So what Worth a look for any firm whose confidentiality rules make sending matter content to a third-party AI cloud a non-starter.

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

Commits in this thread

1 commit from brauliogusmao/mike, oldest first. Source extracted verbatim from the harvested git log.

SHA	Subject	Author	Date
`cb3e3b59`	feat: integração com Ollama para modelos locais	Braulio Gabriel Gusmao	2026-05-13	↗ GitHub
commit body Adiciona suporte a modelos rodando localmente via Ollama, com estratégia de pré-carregamento de documentos no contexto antes da chamada ao LLM - necessário porque modelos menores não lidam bem com tool calling reativo. - Backend: adapter de streaming (ollama.ts), rota GET /ollama/models, dispatcher atualizado para provider "ollama/", models.ts e types.ts atualizados - Frontend: grupo "Local (Ollama)" dinâmico no ModelToggle, busca de modelos via fetchOllamaModels(), useSelectedModel aceita IDs ollama/*, modelAvailability atualizado para provider ollama Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

SHA

Subject

Author

Date

cb3e3b59

feat: integração com Ollama para modelos locais

Braulio Gabriel Gusmao

2026-05-13

↗ GitHub

commit body

Adiciona suporte a modelos rodando localmente via Ollama, com estratégia
de pré-carregamento de documentos no contexto antes da chamada ao LLM -
necessário porque modelos menores não lidam bem com tool calling reativo.

- Backend: adapter de streaming (ollama.ts), rota GET /ollama/models,
  dispatcher atualizado para provider "ollama/", models.ts e types.ts
  atualizados
- Frontend: grupo "Local (Ollama)" dinâmico no ModelToggle, busca de
  modelos via fetchOllamaModels(), useSelectedModel aceita IDs ollama/*,
  modelAvailability atualizado para provider ollama

Co-Authored-By: Claude Sonnet 4.6 <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-456.md from inside the repo you want the changes in.