Focus67Dumby: A 100% Offline, Vision-Aware Sticky Note That Tells Coding Tutorials from Brain-Rot

Описание и применение

Focus67Dumby — автономный десктопный виджет, использующий локальные модели Ollama для различения учебных видео и отвлекающих сайтов, обеспечивая конфиденциальность и гибкие напоминания.

Задача

Developers struggle to stay focused on coding tutorials without falling into YouTube rabbit holes, and existing blockers either over‑block or rely on cloud AI that compromises privacy.

Результат

Focus67Dumby provides a privacy‑first, offline productivity aid that accurately detects coding tutorials versus distractions, offering configurable nudges without cloud telemetry.

Рабочий процесс

• 1. Install Focus67Dumby and Ollama locally.
• 2. Lock in a task and sprint duration on the sticky note.
• 3. Select a local model from the dropdown.
• 4. The app watches active windows and captures 512x288 screenshots.
• 5. The chosen model classifies content as productive or distracting.
• 6. If distraction detected, the app triggers a configured interference level (toast, sound, or popup).

Доказательства

Focus67Dumby is an ultra-lightweight, 100% offline floating sticky-note accountability companion powered by local open-weight models (gemma4:e2b, gemma4:e4b, qwen3-vl:2b, gemma3:1b, and gemma3:270m) via Ollama.

Источник

It sits quietly in the corner of your screen like a minimalist 350x530 dark-amber sticky note. You lock in what you are working on, pick a sprint duration (25m), and choose your local Ollama model. In the background, it observes your active window transitions and downscaled in-memory screenshots (512x288) to distinguish productive work and relevant tutorials from off-task entertainment—nudging you back on track without ever sending a single byte of data to the cloud.

Источник