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

A developer built SlothDesk, a local-first desktop dashboard that uses Hugging Face smolagents and a locally hosted Qwen2.5-7B-Instruct model via LM Studio to propose an organization plan for a cluttered Downloads folder. The tool separates AI reasoning from filesystem mutation, requiring explicit user confirmation before any move and writing an immutable JSON audit manifest that supports one-click undo. The developer reports running the 7B model at Q4_K_M quantization on an 8 GB VRAM laptop GPU and says the app was built with pair-programming assistance from Google Antigravity.

This is a submission for the DEV Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady https://dev.to/challenges . SlothDesk is a local-first, desktop-style dashboard that rewards laziness by safely organizing your cluttered Downloads folder with minimal user effort. Tagline: Less sorting. More living. Downloads folders are notorious black holes where productivity goes to die. Files of every kind—invoices, design assets, archives, code scripts, and firmware—pile up in an unmanageable mess. Existing tools typically fall into two extremes: SlothDesk charts a different path: Slow and Steady . It runs completely offline using Hugging Face smolagents and LM Studio Qwen2.5-7B-Instruct , treating the language model as an untrusted reasoning engine rather than a reckless file manipulator. Downloads/ ├── Documents/ ├── Images/ ├── Videos/ ├── Audio/ ├── Archives/ ├── Code/ └── Other/ Many AI file organizers give the model direct write tools or shell access CodeAgent , shutil.rmtree , os.rename . If the model hallucinates or encounters ambiguous context, files can be permanently destroyed. In SlothDesk, filesystem mutation is architecturally separated from AI reasoning: get file metadata filename get allowed categories validate category category SLOTHDESK ROOT . Any path containing .. , absolute drive letters, or symbolic links is immediately rejected. {name} {counter}{ext} e.g. invoice october 1.pdf . Inspect loose files in the Downloads folder, track storage volume, and verify the local inference engine status at a glance. Clicking Scan & Propose Plan triggers smolagents via LM Studio. Every file receives a color-coded category badge, destination path preview, model rationale, and automatic collision resolution. Zero files are altered until the user explicitly reviews the plan summary and safety checklist, confirming the moves in a dedicated modal dialog. Inspect all top-level files with real-time size metrics, extension detection, and SHA-256 verification hashes. Every move produces an immutable JSON audit manifest. Click Undo Operation to instantly restore files back to their exact original root locations. smolagents ToolCallingAgent Qwen2.5-7B-Instruct GGUF Q4 K M on consumer hardware NVIDIA RTX 5050 Laptop GPU / 8 GB VRAM . 0a130e and soft lime accents 84cc16 . infra/compose.yaml . A key requirement of SlothDesk is honesty: This application was designed, implemented, and hardened pair-programming with Google Antigravity . In accordance with DEV community guidelines, ai disclosure level: some ai is declared for this submission. 1.ext guaranteeing zero overwrites. smolagents.ToolCallingAgent over local LM Studio endpoints pytest and validated the production build. docs/ARCHITECTURE.md docs/SECURITY TESTING.md docs/DEMO SCRIPT.md