slothnotes: let a tiny local model read your notes so you don’t have to

Описание и применение

slothnotes – это CLI‑инструмент, который локально обрабатывает заметки, используя небольшую модель Qwen2.5‑0.5B‑Instruct, и выводит краткое резюме каждой записи.

Задача

Users have many notes they never reread and spend time opening each file to remember its content.

Результат

On an 8‑core CPU, slothnotes summarized four sample notes in about 3 seconds, saving the user the time of opening each file.

Рабочий процесс

• Point slothnotes at a folder of .md or .txt files
• The CLI loads a Qwen2.5‑0.5B‑Instruct GGUF model via llama.cpp
• It runs one prompt per note and outputs a summary line
• Optionally writes a digest.md containing all summaries

Доказательства

It runs a small open‑weight model (Qwen2.5-0.5B-Instruct, Q4_K_M GGUF, about 490 MB) on the CPU through llama.cpp.

Источник

On an 8-core CPU with no GPU, it summarized all four in about 3 seconds.

Источник

The tiny model got a grocery detail wrong. It listed "half a loaf of bread" when the note actually says to skip bread.

Источник