brauliogusmao plugs Ollama into Mike for local-model runs

The fork can now talk to models running on your own machine, not just remote APIs.

infrastructuresecurity

Braulio Gusmão has added Ollama - a tool for running open-source language models locally - as a first-class option inside Mike. The model picker now shows a 'Local (Ollama)' group that fills itself in based on whatever models you happen to have installed on the machine, sitting alongside the existing remote providers rather than replacing them.

The more interesting move is how documents get to the model. Instead of letting the model decide mid-conversation to go fetch a document - the standard pattern with the bigger commercial models - Mike now loads the relevant documents into the prompt up front. The reasoning is honest: the smaller models you can realistically run on a laptop or office server aren't reliable at that kind of mid-flight tool use, so the integration just hands them everything they need at the start.

So what Worth a look for any legal team that wants to keep client documents off third-party servers without giving up on AI-assisted work.

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 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

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>

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.

⬇ Download capture-thread-456.md