SlothDesk — Local-First AI Downloads Organizer: Less sorting. More living.

Description and use

SlothDesk is a local‑first AI downloads organizer that offline sorts files into subfolders, guarantees safety with hash checks, collision handling, and reversible manifests, and requires user approval before any file moves.

Problem

Downloads folders become cluttered messes where productivity is lost, and existing tools either rely on fragile regex scripts or upload private files to cloud AI services.

Outcome

SlothDesk achieves safe, offline organization of the Downloads folder with zero file overwrites, deterministic collision handling, cryptographic integrity checks, and reversible manifests, all while keeping private data local.

Workflow

• Scan Downloads folder and compute SHA‑256 hashes and sizes
• Invoke smolagents via LM Studio to generate a read‑only proposal with category badges and destination paths
• Present proposal to user with color‑coded badges and rationale
• User reviews proposal and confirms moves in an explicit approval modal
• At execution, re‑verify hashes, enforce path confinement, resolve collisions, and move files
• Generate immutable JSON audit manifest for each move
• Provide one‑click undo to restore original locations

Evidence

SlothDesk charts a different path: Slow and Steady. It runs completely offline using Hugging Face smolagents and LM Studio (Qwen2.5-7B-Instruct)

Source

Zero files are altered until the user explicitly reviews the plan summary and safety checklist, confirming the moves in a dedicated modal dialog.

Source

Existing files are never overwritten.

Source

At scan time, SlothDesk computes the SHA-256 hash and byte size of every file. At execution time, it re-verifies these hashes.

Source