Overnight Sloth: Wake Up to What Matters, Ignore the Noise

Описание и применение

Overnight Sloth — локальный агент, который ночью обрабатывает экспортированные чаты и письма, удаляет шум и выдаёт двухстрочное резюме, экономя время утром.

Задача

Users waste mental energy scrolling through thousands of unread messages each morning to find actionable items.

Результат

Processing a 400-message group chat overnight produced a two-line summary that saved the user 15–20 minutes of reading time and restored calm focus for the day.

Рабочий процесс

• 1. Export chat logs or email threads to a monitored directory.
• 2. Watchdog script detects new files and triggers processing.
• 3. Noise Filter Agent removes emojis, stickers, and irrelevant banter.
• 4. Executive Summarizer Agent condenses core discussion into two bullets.
• 5. Summary is written to a desktop file for the user to view upon waking.

Доказательства

Every night, it ingests chaotic group chat exports, long email threads, or cluttered message logs, filters out the memes and small talk, and leaves a clean, two-bullet summary waiting on your desktop when you wake up.

Источник

Instead of starting your morning scrolling through 300+ unread messages just to see if plans changed or if you were assigned a task, Overnight Sloth does the heavy lifting while you sleep, rewarding your inner sloth with zero-effort morning catch-ups.

Источник

Overnight Sloth is built entirely around an open-source, local-first AI stack: LLM Engine: Powered by Ollama, running a quantized Llama-3.1-8B-Instruct model locally on-device.

Источник

A background Python script using the watchdog library monitors local export directories overnight, automatically kicking off processing whenever new chat logs are dropped in.

Источник

This week, I tested it on a high-activity group chat that accumulated over 400 messages overnight. Instead of spending 15 to 20 minutes reading through banter, I opened my desktop to a precise two-line brief highlighting a single deployment deadline change and one direct question addressed to me.

Источник