SlothDesk: A Lazy, Offline AI That Cleans Your Downloads Folder

Description and use

SlothDesk automatically sorts and renames files in a local folder using a small LLM, keeping all operations offline and private.

Problem

Users have messy download folders with unnamed or poorly named files that are hard to organize manually.

Outcome

SlothDesk automatically organizes and renames files in a local folder using a small 3B open‑weight model, keeping all processing offline and private.

Workflow

• Select folder in Streamlit UI
• Scan folder and extract first 600 characters of supported file types
• Send preview to local Ollama model with Pydantic schema for structured output
• Display dry‑run table with proposed moves, renames, and reasoning
• User reviews and approves plan
• Apply file moves and renames

Evidence

SlothDesk is a private, local-first AI file organizer. It reads a short text preview of the files in a messy folder...

Source

Reads the first 600 characters of .pdf, .txt, .md, .csv, .json, and .py files to understand what they actually are

Source

Sorts each file into one of seven categories: Invoices & Receipts, Work & Documents, Code & Dev, Personal & Identity, Media & Assets, Archives & Installers, or Miscellaneous

Source

SlothDesk runs locally, so there's no hosted link. You can try it yourself in a few minutes with the steps in the README.

Source

The whole project is built around open-source tools that run on a normal laptop.

Source