stakwork/mikeoss

Maintained by Paul Itoi · verified on MikeWatch

Ollama local inference, voice input, and Docker deployment - infrastructure-focused fork

Five topics tracked. Ollama provider support spans two Hive-generated PRs: e88d06b0 (backend adapter, routing, model list endpoint) and c629bb00 (frontend picker, account section, tool-unavailability notice). Voice input (Evanfeenstra) adds a mic button to ChatInput. Docker setup adds multi-stage Dockerfiles and compose files for local and production. Work is automated-authoring-heavy - several PRs opened and merged within seconds.

View on GitHub →

stakwork/mikeoss is active across several infrastructure tracks. The biggest is full Ollama support: backend adapter with OpenAI-compat shim, model discovery via a new /user/ollama-models endpoint, and a frontend model picker and account section. Tools are stripped on Ollama models with a visible notice. Alongside that, a mic button lands on the chat composer for voice dictation, and Docker support covers both local dev and production builds.

What's in it

Local inference via Ollama A provider adapter lets the fork route chats to a model running on your own hardware instead of a hosted API, with model listing and routing wired in.
Voice input in chat A mic button on the chat box uses speech recognition so users can dictate prompts instead of typing them.
Ollama model picker polish Targeted UI work on the model picker that appears once Ollama is in play, alongside an unavailable-state for account settings tools.
Docker setup for dev and prod A containerised setup intended to cover both local development and production deployment of the fork.

Direction

infrastructurechat-uiintegration

Activity

Themed changes and pull requests touching this fork, newest first. Themed changes that haven't been turned into a public post yet still appear — they're real work even without a published writeup.

✅ #3 Generated with Hive: Add voice input with mic button and speech recognition to ChatInput +968 -25 2mo ago self by Evanfeenstra ↗ analysis ↗ GitHub

Add voice input with mic button and speech recognition to ChatInput

✅ #5 Generated with Hive: Add Ollama model picker, account settings section, and tool-unavailability notice to UI +200 -23 2mo ago self by pitoi ↗ analysis ↗ GitHub

✅ #4 Generated with Hive: Add Ollama LLM provider adapter, routing, and model list endpoint +928 -30 2mo ago self by pitoi ↗ analysis ↗ GitHub

Generated with Hive: Add Ollama LLM provider adapter, routing, and model list endpoint

📝 stakwork teaches Mike to run on local models 2 commits 2mo ago infrastructuresecurity draft

A pair of merged changes let this fork point Mike at open models running on your own hardware instead of a cloud provider.

🟢 #2 Generated with Hive: Add docker directory with local dev compose, setup scripts, and production Dockerfiles +1,005 3mo ago self by Evanfeenstra ↗ analysis ↗ GitHub

⛔ #1 feat: configure supabase +454 3mo ago by fayekelmith ↗ GitHub

📝 Ollama model picker and account settings unavailable UI 0 commits — minor change

📝 Docker setup for local dev and production 0 commits — minor change

📝 Ollama wired in as a local LLM provider with routing and model discovery 0 commits — infrastructuresecurity draft

stakwork/mikeoss adds Ollama as a first-class provider alongside Claude and Gemini. The change covers the backend adapter, request routing, and a new endpoint that enumerates installed models from the Ollama server.

📝 Mic button added to chat composer for voice input via speech recognition 0 commits — chat-ui draft

Evanfeenstra adds a microphone button to the ChatInput component, letting users dictate prompts instead of typing. The change is frontend-only and keeps everything downstream of the text field unchanged.

Threads of work (detailed view)

4 threads have been distilled into posts.

stakwork teaches Mike to run on local models

A pair of merged changes let this fork point Mike at open models running on your own hardware instead of a cloud provider.

infrastructuresecurity

2 commits · latest 2mo ago

Full Ollama provider support: backend adapter, model discovery, and frontend picker

Two Hive-generated PRs in stakwork/mikeoss add end-to-end Ollama support. The backend adapter routes `ollama/*` model ids to a local Ollama server, the frontend gets a model picker group and an account settings section, and tools are stripped with a visible warning when a local model is selected.

infrastructurechat-ui

2 commits · latest 2mo ago