🦥 SlothChat: An Offline, Open-Weight AI for Your Group Chat Overload.

Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady Submission 🦥

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady.

SlothChat is a local-first, privacy-focused AI tool that reads your chaotic group chats overnight and hands you a clean, 3-bullet summary with action items in the morning.

We all have that one group chat—the one with 150 unread messages about inside jokes, server crashes, and "who's bringing what." Instead of scrolling for 20 minutes to catch up, SlothChat does the heavy lifting. It takes the messy chat log and extracts the signal from the noise, saving you from the mental drain of catching up.

GitHub Repository: https://github.com/Dexter-6666/slothchat

The core of SlothChat is a local inference pipeline running the Qwen 2.5 1.5B model via HuggingFace transformers.

Instead of sending your private group chats to a closed API, the entire process runs on your machine (or a free Colab instance). The script wraps the chat log in a highly specific system prompt, forcing the model to output a strict JSON-like bulleted format with zero yapping.

I used Python and PyTorch to tie it together. The model runs offline, ensuring that once it's loaded, no data ever leaves your local environment.

Overnight group chats are the absolute worst thing to paste into a closed, rented model. It contains sensitive context, personal names, and half-baked plans.

Running an open-weight model locally changes that entirely:

SlothChat embodies the sloth lifestyle. It sits quietly, consumes zero cloud resources, and does the heavy cognitive lifting so I don't have to. I've traded the anxiety of a red notification badge for a clean, 3-line summary.

Tech Stack: Python, HuggingFace Transformers, Qwen 2.5 (Open-Weight), PyTorch.