Slothdigest: An overnight morning-digest agent that run fully local

Description and use

Slothdigest is a local AI agent that processes notes, emails, and chat logs overnight to produce a three‑task morning brief in 34 seconds.

Problem

Organizing scattered notes, emails, and chat logs into a concise morning brief of top priorities.

Outcome

Three prioritized tasks were generated from 1,891 characters across three files in 34 seconds, with the process remaining fully local and privacy‑preserving.

Workflow

• Drop files into an inbox/ folder
• Run npx tsx src/index.ts
• The script sends each file to Gemma 3 (1B) via Ollama
• Gemma returns strict JSON with summary and tasks
• Zod validates the JSON
• Tasks are merged, deduplicated, sorted by deadline
• Top three tasks are written to brief.json and an HTML page

Evidence

Most of what's due this week is buried in group chats, notes and copied emails, between jokes and shopping lists.

Source

I drop files into an inbox/ folder and run one command. On my test inbox (a short email, a group chat of about 35 lines, and a notes file: 1,891 characters in total) a 1B-parameter Gemma model running on my own laptop produced three priorities in 34 seconds.

Source

For each file it asks Gemma 3 (1B), running locally through Ollama, for strict JSON: a one-sentence summary and a list of tasks with deadlines.

Source

A 1B model is easy to demo and hard to trust. Here are five ways mine broke, and the boring code that handles each: ...

Source

My files go from disk to a model process on localhost. No account, no API key, nothing uploaded.

Source