Loading page...Загружаем страницу...正在加载页面...
AtlasRepo

EchoLantern: A Private Little Archive for Memories

Description and use

EchoLantern lets users create memory keepsakes locally with Gemma 3 1B, storing data in browser storage and keeping privacy intact.

Problem

Users want AI‑assisted memory writing without sending personal notes to a hosted service.

Outcome

EchoLantern enables private, AI‑assisted memory creation without external data transmission, while keeping the original note visible and allowing user edits.

Workflow

  • 1. Open EchoLantern locally via Node server.
  • 2. Enter rough notes and optional photo.
  • 3. Click generate to invoke Ollama with Gemma 3 1B and a JSON schema.
  • 4. Review the draft keepsake, edit if needed.
  • 5. Save to local archive in browser storage.
  • 6. Export archive as Markdown or JSON if desired.

Evidence

EchoLantern is a local‑first keepsake maker for everyday memories, people, places, pets, family stories, and meaningful objects or traditions.

Source

When run locally, the server uses Gemma 3 1B with an explicit JSON schema to return a consistent keepsake structure.

Source

The app has no user account or hosted AI endpoint.

Source

The current automated suite has 19 passing Node.js tests covering input validation, prompt boundaries, output parsing, template fallback, mocked Ollama integration, and HTTP error/security cases.

Source

  • Record date: 2026-10-27T06:11:11.961Z