Midzimu: Keeping Family Stories Close with Local AI

Description and use

Midzimu is an offline‑first family archive that stores data in the browser and offers optional local AI via Ollama for summarization, theme suggestion, and translation, keeping user data on the device.

Problem

Families need a way to preserve oral histories, recordings, and traditions locally without relying on cloud services or mandatory AI integration.

Outcome

Midzimu provides a fully local, offline‑first archive for family stories, with optional AI features that run on a user‑controlled Ollama instance, ensuring data privacy and control.

Workflow

• Install the app locally by running python -m http.server 4173 --bind 127.0.0.1 and opening http://127.0.0.1:4173
• Create or edit stories and record audio directly in the browser
• Configure a local Ollama server address if AI assistance is desired
• Use the AI helper to draft summaries, suggest themes, or translate transcripts
• Back up or restore data via the app’s backup feature

Evidence

Midzimu is an offline-first family oral-history archive for preserving memories, proverbs, traditional practices, recipes, and the words elders choose to share.

Source

The optional AI helper sends a transcript to an Ollama server at the address the user configures. It can draft a summary, suggest themes, and translate into a chosen language.

Source

Story text and recordings are stored in the browser's IndexedDB. A service worker caches the app shell for offline visits after the first load.

Source

With Ollama running locally, the story text stays on the user's device; a remote Ollama address would receive it, so users should only configure an endpoint they trust.

Source