Namakemono なまけもの — I built a local sloth to read my Japanese paperwork so I don't have to

Salugu Harshita Bhanu — Sat, 24 Oct 2026 21:49:54 +0000

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady

What I Built

Hi there ! in about a year I'm moving to Japan for my first job. I've been studying Japanese on Duolingo. I know enough to order food and embarrass myself at a convenience store. I do not know enough to parse a letter from the ward office about my residence registration deadline.
Namakemono (なまけもの — Japanese for sloth) is a local CLI that reads Japanese official paperwork and digests it into plain English. You drop .txt files into an inbox/ folder, run one command, and get:

out/digest.md — documents sorted by urgency, each with a 2-sentence English summary, an action checklist, what to bring, and 5 key Japanese terms with readings
out/deadlines.ics — a calendar file you can import into Google Calendar or Apple Calendar
Per-file JSON cache, so the second run is instant The whole thing runs locally on my laptop using Gemma 3 4B via Ollama. No internet. No API key. No subscription. One Python file. Who gets to be lazier? Me, when I move to Japan. And hopefully anyone else drowning in official Japanese letters. ## Demo The full source is on GitHub — clone it, drop a Japanese .txt into inbox/, and run it yourself: 👉 github.com/Git-brintsi20/Namakemono-

Sanpo 散歩: I built a local Japanese tutor from my phone gallery at midnight — no cloud, no walk needed

Salugu Harshita Bhanu — Mon, 12 Oct 2026 06:38:19 +0000

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass

What I Built

I'm in my final year of B.Tech. Next year I move to Japan for my first job, and somewhere between the offer letter and the packing list I realised I'm about to leave behind the places that made me — Vizag's beaches, Araku valley mornings, the smell of home.

Sanpo (散歩, "a stroll") is a walking companion that runs entirely on my laptop. You take photos — from a real walk, or from your phone gallery at midnight — and a local Gemma 3 vision model turns what it sees into Japanese flashcards: the word, the hiragana reading, romaji, an example sentence, and a note on how that thing might feel different in Japan. At the end, it writes a short postcard from you to yourself, sealed until your first week in Japan.

Everything — the AI, your photos, your letters — stays on your device. No cloud. No API key. No account.

There's also a weather-based walk quest (Open-Meteo, no key needed), and a personal bucket list of places I want to see before I leave India — RK Beach, Araku Valley, Borra Caves, Dudhsagar Falls, Darjeeling...

I couldn't go outside — it was midnight. So I used what I had: a rainy windshield from a monsoon drive, my room with Diwali string lights and a suitcase in the corner, a yellow rose, an idli-dosa thali, my boots, and a piece of art I love. The model found words in all of them.

Demo

Code

Git-brintsi20 / Sanpo

A bit of something Before I leave here and begin Again .

散歩 Sanpo — Before I Go

A local-first walking companion. Walk anywhere, photograph what you see, learn it in Japanese, write a postcard to your future self.

Demo: ▶ Watch on YouTube
Live post: DEV.to — Hacktoberfest Week 1 submission

What it does

Feature	Description
📸 Photo → Japanese Cards	Upload walk photos. A local Gemma 3 vision model picks 3 objects and returns word cards: Japanese, hiragana, romaji, example sentence, Japan note
🔊 Pronunciation	Hit the speaker button on any card to hear it in Japanese via Web Speech API (`ja-JP`)
✉️ Postcard to Future Me	At the end of a walk, Gemma writes a short letter from you to yourself — sealed until a date you choose
🎯 Weather Quest	Fetches local weather (Open-Meteo, no key) and gives you a walk quest suited to the day
📋 Bucket List	Personal places to visit before leaving India

…

View on GitHub

How I Built It

Model: Gemma 3 4B (vision), served locally by Ollama. Everything runs on CPU — 32 GB RAM, no GPU.
App: Next.js 14 (App Router) + TypeScript + Tailwind CSS. Three API routes call Ollama at localhost:11434 — vision analysis, postcard writing, and weather quests.
Speed: On CPU, gemma3:4b took between 10.4s and 65s per photo. Simple images (boots: 10.4s, food: 13.7s) were fast. Complex ones (room with Diwali lights: 65.3s) took longer. Client-side resize to 768px before sending was the biggest single speed win.
Extras: Open-Meteo for weather (no key), Web Speech API for ja-JP pronunciation, localStorage for all walks and postcards. Zero external dependencies for AI.
12B model: Didn't have disk space for gemma3:12b (~8 GB needed). Ran everything on 4B — for everyday objects, it was more than enough.
What actually went wrong: Two real mistakes. A rainy windshield photo returned あられ (arare), labeled "Raindrops" — but あられ means hailstones. Raindrops are 雨粒 (amatsubu). And a yellow food plate returned ヒマワリ (himawari) labeled "Marigold" — himawari means sunflower. The model saw yellow, guessed flower, got both the word and the English wrong. I kept them in. That's honest.

The postcard Gemma wrote me (sealed until 12 October 2027):

"It's strange, isn't it? This morning walk felt so familiar, even though I'm so far from Vizag. I spent a while just appreciating the bara and ha — the cherry blossoms and leaves. I learned words like arare, Iruminēshon, and Suitukēsu. I'm feeling a little quiet and wishful, a little homesick perhaps. It's a lot, but I'm trying to be patient. — You, today"

It hallucinated a lake. But the homesick part it got exactly right.

Why Does Open Innovation Matter?

A postcard to my future self is about as personal as data gets. With an open-weight model running locally, my photos and letters never leave my laptop. I don't pay per token for something I want to reread in a year.

It also runs on weak hardware with no internet after setup. The model is honest about being small — it mistakes hailstones for raindrops — and somehow that feels more trustworthy than a polished API that hides its errors.

These are the memories that will keep me company when I feel lonely in Japan one day, missing home. Building something that holds them felt right.

Prize Categories

Best Use of Gemma

DEV Community: Salugu Harshita Bhanu

Namakemono なまけもの — I built a local sloth to read my Japanese paperwork so I don't have to

What I Built

Sanpo 散歩: I built a local Japanese tutor from my phone gallery at midnight — no cloud, no walk needed

What I Built

Demo

Code

Git-brintsi20 / Sanpo

A bit of something Before I leave here and begin Again .

散歩 Sanpo — Before I Go

What it does

How I Built It

Why Does Open Innovation Matter?

Prize Categories