{"slug": "slothnotes-let-a-tiny-local-model-read-your-notes-so-you-don-t-have-to", "title": "slothnotes: let a tiny local model read your notes so you don't have to", "summary": "A developer built slothnotes, a small Python CLI that summarizes folders of Markdown and text notes using a locally run Qwen2.5-0.5B-Instruct model (Q4_K_M GGUF, about 490 MB) via llama.cpp on the CPU, with no API key or network required after download. On an 8-core CPU without a GPU, it summarized four sample notes in about three seconds, though the tiny model misreported a grocery detail, listing bread the note said to skip. The MIT-licensed tool accepts any GGUF through a --model flag and includes three pytest tests and a GitLab CI job.", "body_md": "*This is a submission for the [Hacktoberfest Open-Source AI Challenge: Week 3](https://dev.to/challenges/hacktoberfest-week3-2026-10-19): Slow and Steady.*\n\nI have a folder full of notes I never reread. Standups. A grocery list. An email to my landlord. Book club plans.\n\nslothnotes is a small Python CLI that reads that folder for me. You point it at a folder of `.md` or `.txt` files. It prints one summary line per note. If you want, it also writes a `digest.md` you can skim in about ten seconds.\n\nIt runs a small open-weight model (Qwen2.5-0.5B-Instruct, Q4_K_M GGUF, about 490 MB) on the CPU through llama.cpp. After the model download, it needs no API key and no network.\n\nThe effort it saves is the boring part: opening every file to remember what was in it. One command does that.\n\nThis is a real run on four sample notes: standup, groceries, landlord, book club. On an 8-core CPU with no GPU, it summarized all four in about 3 seconds.\n\nOne honest limit: the tiny model got a grocery detail wrong. It listed \"half a loaf of bread\" when the note actually says to skip bread. A bigger GGUF should be more accurate, but it will be slower. For a quick skim it's fine. For anything that matters, read the note.\n\n[https://gitlab.com/engelstands-hue/slothnotes](https://gitlab.com/engelstands-hue/slothnotes)\n\nMIT licensed. It has a README, three pytest tests that run without the model, and a GitLab CI job.\n\n`--model` takes any GGUF, so you can swap models without touching code.\nTo try it:\n\n```\npip install llama-cpp-python --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu\ncurl -L -o models/qwen2.5-0.5b-instruct-q4_k_m.gguf https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct-GGUF/resolve/main/qwen2.5-0.5b-instruct-q4_k_m.gguf\npython slothnotes.py demo_notes --out digest.md\n```\n\nNotes are personal. Standups, landlord emails, grocery lists. Because slothnotes runs an open-weight model locally, none of that leaves the machine. It works offline, and each run costs nothing. Since the model is open, you can swap in a bigger or fine-tuned one with a single flag.\n\nA closed API would mean an account, a key, a bill, and sending my notes to someone else's server. For a tool whose whole point is being lazy, that's too much setup.\n\nNone. This entry doesn't use partner technology.\n\nMore of what I build: [https://engelailabs.com](https://engelailabs.com)", "url": "https://wpnews.pro/news/slothnotes-let-a-tiny-local-model-read-your-notes-so-you-don-t-have-to", "canonical_source": "https://dev.to/productivityforge/slothnotes-let-a-tiny-local-model-read-your-notes-so-you-dont-have-to-1o8k", "published_at": "2026-10-25 14:43:12+00:00", "updated_at": "2026-10-25 14:44:54.229288+00:00", "lang": "en", "topics": ["ai-tools", "large-language-models", "ai-products", "developer-tools"], "entities": ["slothnotes", "Qwen2.5-0.5B-Instruct", "llama.cpp", "GitLab", "Hacktoberfest", "engelailabs.com"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/slothnotes-let-a-tiny-local-model-read-your-notes-so-you-don-t-have-to", "markdown": "https://wpnews.pro/news/slothnotes-let-a-tiny-local-model-read-your-notes-so-you-don-t-have-to.md", "text": "https://wpnews.pro/news/slothnotes-let-a-tiny-local-model-read-your-notes-so-you-don-t-have-to.txt", "jsonld": "https://wpnews.pro/news/slothnotes-let-a-tiny-local-model-read-your-notes-so-you-don-t-have-to.jsonld"}}