SlothDesk: Zero-Cloud, Zero-Cost Autonomous Desktop Organization with Open-Source AI

A developer built SlothDesk, an open-source, local-first tool that autonomously sorts, renames and files cluttered Desktop and Downloads folders without sending data to any cloud service. The system combines scikit-learn TF-IDF semantic vector classification with heuristic entity and date extractors, running at under 15 milliseconds per file with less than 200MB of RAM overhead, and uses a Watchdog-powered daemon that waits for downloads to finish before acting. In a test on a real Downloads folder of 42 files accumulated over three weeks, the tool organized the clutter locally, keeping confidential documents such as bank statements and tax returns off third-party servers.

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady SlothDesk is an open-source, local-first autonomous desktop and downloads clutter janitor built for anyone who hates organizing files by hand. Every single week, our Desktop and Downloads folders become digital landfills of: Screenshot 2026-10-24 at 11.23.41 PM.png statement 2 .pdf Uber trip receipt e83912.pdf customers dump 2026 raw.csv docker-compose.staging.yml node-v22.1.0-x64.msi Manually inspecting, renaming, and filing hundreds of files is the ultimate procrastination trap. Instead of making you drag, click, and rename files: 1 with extracted vendor names, dates, and semantic slugs. The Open-Source Local AI Janitor for Chaotic Desktops and Downloads. Channel your inner sloth. Open-source local inference sorts, renames, and files your digital clutter so you don't have to. Every developer and knowledge worker's Desktop and Downloads folders devolve into a chaotic digital landfill: Manually organizing hundreds of files is the ultimate procrastination chore. SlothDesk automates this entirely on your machine. Using open-source natural language processing and semantic vector classification scikit-learn TF-IDF semantic vector anchors + heuristic entity and date extractors , SlothDesk automatically: chase bank statement 2026-10.pdf , uber receipt 2026-10-24.pdf , aws screenshot 2026-10-24.png . Repository : https://github.com/titas-mahato/slothdesk https://github.com/titas-mahato/slothdesk The repository is structured with a modular local inference architecture: app/classifier.py scikit-learn TF-IDF semantic vector anchors + local keyword extractor app/renamer.py Entity, date, and vendor extraction engine app/janitor.py Virtual desktop simulation + safe real filesystem operations with conflict resolution app/daemon.py Watchdog-powered background daemon with patient file settling main.py & templates/index.html FastAPI + responsive dark-canopy editorial dashboard scikit-learn TF-IDF vectorization mapped against domain anchor spaces . It computes cosine similarity distances across document categories in under 15 milliseconds per file with $< 200\text{MB}$ RAM overhead. YYYY-MM-DD , Month YYYY , recognized tech/service vendors Chase , Uber , AWS , Stripe , GitHub , and file roles to synthesize clean, normalized filenames. watchdog library. When a new file is detected in Downloads , the daemon waits patiently for a quiet window to ensure the browser has finished writing .crdownload or temporary files before taking action. Desktop folders contain your most confidential documents: bank statements, tax returns W-2/1099 , medical receipts, payslips, and private source code. Handing these files over to third-party commercial LLM clouds creates unacceptable privacy risks. Open-source local AI ensures your private files never touch a server you don't control. During testing this week, SlothDesk was set loose on a real Downloads folder containing 42 untidy files accumulated over three weeks: