Home / use case

Branching conversation graphs with OpenYoke

What they built

OpenYoke is an open-source Ollama desktop app that treats a conversation as a tree. You can branch from any earlier point and view the whole thing as an n8n-style canvas.

When you branch, the model only sees messages along that path, so competing ideas don't contaminate each other. Everything stays on your machine.

Setup

  • Tauri shell with Rust backend (no Electron)
  • Ollama at http://127.0.0.1:11434
  • macOS, Windows, Linux

How it works

  1. Each node is one question and answer; pan, zoom and branch anywhere
  2. Models are browsed, pulled and deleted from the in-app Models tab
  3. Conversations and settings are saved as JSON in a folder you choose

Do it yourself

  1. Install Ollama (brew, winget or the install script) and run `ollama serve`
  2. Build or run OpenYoke and choose a storage folder
  3. Pull a model from the Models tab
  4. Branch from any node to compare approaches
Source: GitHub · Added 2026-10-18. This write-up summarizes the original source; see it for full details.

Related

Auto-tagging documents in Paperless-ngx with Ollama

Since version 3.0, Paperless-ngx suggests titles, senders, document types and tags, and can chat with your documents, using a local Ollama model.

bettersorted.de · 2026-10-01

Home Assistant Voice PE with a local LLM instead of Echo

A $60 Voice Preview Edition, an N100 box and an optional RTX 3060 replace every Echo and Nest in the house. It keeps working with the internet unplugged.

jpk.io · 2026-06-10

A private ChatGPT for a family of four on a Mac mini

One always-on M4 Mac mini serves Open WebUI to every phone and laptop in the house. Kids get a tutor preset, and three AI subscriptions are gone.

Think Different · 2026-06-07

Fully local Home Assistant voice assistant on a GPU

Wake word to spoken answer in 2-3 seconds, with zero audio leaving the house. Built from faster-whisper, Piper and Ollama, with a cloud fallback.

joekarlsson.com · 2026-04-13