I Gave My Forgotten Files a Night Shift—Without Uploading Them

Description and use

SlothShift is a local‑first desktop assistant that scans a folder, uses a locally hosted Gemma model to generate summaries and next‑step suggestions, lets users review and approve them, and exports organized copies and notes—all without uploading files.

Problem

Users have small, forgotten documents that require quick decisions but lack a local, privacy‑preserving workflow to summarize and organize them.

Outcome

Users can batch‑process up to 300 files (10 MB each) locally, producing structured summaries and organized exports while keeping all data on their machine.

Workflow

• Select a folder or use the sample vault
• Start Ollama and pull the gemma4:e2b model if not installed
• Run Night Shift to generate suggestions
• Review each suggestion, edit if needed
• Approve or reject each item
• Export approved items to a ZIP or Lazy Pack

Evidence

Point it at a folder, or start with the built‑in sample vault. A locally running Gemma model (gemma4:e2b through Ollama) reads supported documents and drafts a short summary, a filename, a category, possible dates, and next steps.

Source

The export is meant for the next morning, not for a chat window: organized copies of approved originals, Markdown handoff notes, a JSON manifest with source hashes, optional drafts, and calendar reminders only when a date is an explicit YYYY-MM-DD.

Source

Both send analysis to the local Ollama API, not a hosted LLM. The model returns structured JSON.

Source