I Built slothd: A Local-First, Offline-Capable AI Daemon That Patiently Organizes Your Messy Workspace

说明与用途

slothd 是一个本地、离线的 AI 守护进程，使用快速的 TabPFN 元数据筛选和 Gemma 3 深度文档理解，在不联网的情况下自动整理工作区文件。

问题

Users spend time manually organizing cluttered workspaces, risking privacy by uploading sensitive files to cloud AI services.

结果

slothd organizes 10 test files in under a second, flags 2 clutter anomalies, detects 1 duplicate set, and performs all operations offline with no cloud API calls.

工作流

• Detect keyboard/mouse inactivity
• Scan target directory
• Extract 7 tabular signals
• Run Prior Labs TabPFN triage
• Flag anomalies
• Run Gemma 3 vision/text model via Ollama
• Generate organization plan
• Show dry‑run preview
• Await user approval
• Execute file moves
• Log actions in SQLite WAL
• Update local vector store
• Provide semantic search via Tiger Data pgvector

证据

I built **slothd**, a local-first, offline-capable AI file organizer designed around the philosophy of **"Slow and Steady"**

来源

Uses **Gemma 3** running locally in **Ollama** with strict Pydantic JSON schemas to read PDFs, invoices, and images.

来源

Fast metadata triage (1ms via local 7-signal engine, ~20ms via **Prior Labs TabPFN**) flags anomalies before invoking heavier models.

来源

Every run is a dry-run by default. Every approved move is written to an SQLite WAL log with a unique batch ID.

来源