SlothSort: A Fully Local Open-Weight File Tidier That Organizes Your Downloads While You

Description and use

SlothSort automatically sorts new files into folders using local models without internet access.

Problem

Cluttered directories, especially Downloads folders with random PDFs, unnamed screenshots, and stray documents, are difficult to organize and often left unattended.

Outcome

SlothSort automatically organizes newly added files into appropriate folders with sanitized names, running entirely offline and without external costs.

Workflow

• 1. File watcher loop monitors target folder for new files.
• 2. On file creation, metadata and minimal text are extracted using pypdf or pytesseract.
• 3. Extracted content is sent to a local open-weight model (e.g., Qwen2.5-1.5B or Llama-3.2-1B) via standard inference APIs.
• 4. Model returns JSON with target directory and sanitized file name.
• 5. Script relocates the file to the target folder and renames it accordingly.
• 6. Interactive dashboard logs the event and displays the detected item, summary, and destination path.

Evidence

SlothSort is a lightweight background automation concept designed around the "Slow and Steady" mindset. It passively listens for newly added files, extracts minimal text or metadata, and lets a local open-weight model figure out the proper category and readable name.

Source

The architecture uses Ollama and llama.cpp to host compact, quantized open-weight models such as Qwen2.5-1.5B or Llama-3.2-1B directly on local hardware.

Source

File system monitoring is handled via Python's watchdog library to keep CPU usage negligible while waiting for new files.

Source