SlothSort: Slow & Steady Autonomous Local AI Desktop Tidier

Description and use

SlothSort is a local desktop organizer that uses open‑source Whisper and SmolLM2 models to transcribe audio, categorize files, rename them in snake_case, and produce a morning audio digest—all offline and without cloud data transfer.

Problem

Developers spend hours sorting chaotic downloads, listening to long voice memos, and renaming cryptic files, while cloud AI tools require subscriptions and expose private data.

Outcome

In a test run, SlothSort avoided 35–45 minutes of manual sorting, produced transcripts in seconds, and required only one click to initiate the process, achieving 100% energy conservation for the user.

Workflow

• Drop cluttered files into a folder or use the Lazy Sandbox
• Click "Hibernate & Sort (Lazy Mode)"
• Local Whisper transcribes audio files
• SmolLM2‑360M‑Instruct parses documents and code, categorizes files, and generates snake_case names
• pyttsx3 creates a spoken morning digest
• Rollback history records each transaction for 1‑click undo

Evidence

SlothSort is an autonomous desktop and voice note organizer powered entirely by open‑weight and open‑source AI models running locally on your machine.

Source

During testing this week, I dumped a cluttered directory containing messy receipts, raw group chat exports, python benchmark scripts, and voice memos: Manual Sorting Time Avoided: ~35 to 45 minutes of dragging, reading, listening, and renaming files.

Source

Runs 100% offline with CUDA acceleration on an NVIDIA RTX 3050 Laptop GPU (or CPU) taking under 1.8 GB VRAM.

Source