SlothDesk: The Lazy Person’s Group Chat Summarizer

Description and use

SlothDesk quickly summarizes long exported group chats, highlighting actionable items and ignored content, using the open Gemma LLM and local Ollama execution.

Problem

Users returning to long group chat exports often need to quickly identify actionable items and ignore irrelevant content.

Outcome

Users can quickly identify key actions and ignore noise in large chat exports, reducing time spent on manual reading.

Workflow

• Paste chat export into the web interface
• Backend cleans timestamps, media markers, and repeats
• Model receives trimmed prompt and returns JSON with summary, todo, ignore, reply
• Frontend displays results and offers copyable reply

Evidence

Paste a long WhatsApp export, Slack thread or email chain, and it gives you: a two-line summary of what happened, a short list of what actually needs you, a note on what you can safely ignore, a ready-to-send reply you can copy

Source

The AI is an open-weight Gemma model reached through an OpenAI-compatible chat API. A small cleanup step strips timestamps, "media omitted" lines and repeats, then keeps the most recent part of the chat.

Source

Because the model sits behind one endpoint URL, the same code runs two ways: Locally: Ollama running Gemma, fully offline. Deployed: a hosted Gemma endpoint, with the app on Render using a one-file render.yaml blueprint.

Source