DEV Community: Aryan Garg

A file manager for the lazy

Aryan Garg — Mon, 26 Oct 2026 02:26:09 +0000

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady
20th August is the international Sloth day, and so we shall evolve to sloth. I'm part sloth myself, so I consider myself at home with this challenge.

What I Built

Sloth(epic name ik) is a file manager that automatically sorts files based on name and content, so you will never have to.
This is for anyone who downloads a bunch of files and is too lazy to organise them before it becomes into an absolute mess.

Demo

Code

AryanGarg-beep / sloth

sloth 🦥

A slow, careful, local file organizer for college material.

sloth reads what's inside your notes, slides and scanned handouts. It asks a local Gemma model (through Ollama) which subject and unit each file belongs to, and files it under:

~/Documents/College/<Subject>/Unit <N>/<original filename&gt

Nothing leaves your laptop. sloth only talks to Ollama on 127.0.0.1.
Nothing is deleted or overwritten. Files are only moved. If a name is taken, the file becomes name (2).pdf.
Nothing moves until you say so. Every run is a dry-run plan first.
Everything can be undone. Every batch of moves is logged, and sloth undo puts the files back exactly where they were.

Built for the DEV Hacktoberfest "Slow and Steady" challenge.

Why

A semester leaves you with files called unit 3.pdf, document(3).pdf, scan_0042.pdf and notes_final(1).pdf, all in Downloads. The filename usually doesn't say which subject a file is…

View on GitHub

How I Built It

For this, I have used gemma4:gemma4:e4b-it-qat, which provided small size, fast speeds(average 5-6 secs per file on an intel core ultra 7 256V laptop CPU) with a low memory footprint (4.3GB), while having enough intelligence to not make too many errors (tested against gemma4:e2b and gemma4:a4b-26b)

Libreoffice is used to determine action based on file-type
Tesseract is used to scan the file via OCR, which allows the program to detect data from any file, like pdfs, excel sheets, pictures etc.
first few pages(around 3000 character) are scanned to extract meaning. (because file names are often just a random mix of characters)
This data goes to gemma, which decides what to do.

Why Does Open Innovation Matter?

Biggest one is keeping everything on the system. I dont have the energy to keep vetting the files i'll hand an AI to sort. And I don't wanna worry about giving some sensitive files to an external party either.

Its mine, and I can do whatever I want with it. I made it, I know how it works, I can change it however I want.

The Lazy Payoff

I used to look at my files, sigh, before struggling to find one i need. And this happens a lot, since im too lazy to to actually sort them. This saved me from it all.

Prize Categories

Best use of gemma - Downloaded and tested like 40 gigs of models. Lots of inferencing tricks from their docs are also involved.

Field Notes IRL. Touch the grass!

Aryan Garg — Mon, 12 Oct 2026 03:39:59 +0000

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

My first idea for this challenge was a lamp that lights up when the weather is nice enough to go outside. I dropped it halfway through planning, because getting people outside isn't really the problem.

People already go out. Look around any park or café: half of them are filming reels, checking how the story looks, scrolling while they walk. They're outside, but they're still on the screen.

And I get why. A lot of that phone use comes from a real want: to remember the moment, to make something out of your day. The phone is just the only tool most of us have for that.

So instead of pushing people out the door, Field Notes gives that urge somewhere else to go. You don't film the bird, you say "there's a bird." You don't post, you just talk. And at the end of the day you still get something made from your outing, a journal entry, written for you and not for an audience.

What I Built

Field Notes is a screen-free voice journal. While I'm outside, I press a button on a small homemade recorder and say whatever I notice: "pretty bird out here, gonna get a salad." My phone stays in my pocket the whole time. When I get home, a local app on my laptop transcribes the notes with Whisper, and Gemma 4 turns them into a short journal entry for that outing, with a nudge for next time and a weekly recap.
It also comes with a weather alarm, which tells the user if its a good time to touch grass.

Nothing leaves my laptop. No account, no cloud, no internet needed.(except for weather data if the user wants it)

Code

AryanGarg-beep / touch-grass

Field Notes: a pocket voice recorder (Pico 2 W) and an offline journal app (Whisper + Gemma)

Field Notes

A pocket voice recorder for going outside with your phone put away, and a laptop app that turns what you said into a journal.

The recorder is a Raspberry Pi Pico 2 W with a microphone and one button: press to start a note, press again to stop. Back home, the app copies the notes off, transcribes them with Whisper, and has Gemma (through Ollama) write a journal entry for each outing and a weekly recap. Everything runs on your laptop.

What's here

fieldnotes/
  app.py               the laptop app (a small local web server + window)
  ui.html              its interface
  fonts/               bundled fonts (SIL OFL), so the app loads nothing from the internet
  install_launcher.sh  adds Field Notes to your app launcher
  recorder/main.py     the Pico firmware
record_test.py         5-second mic test for the Pico, to check the wiring

The recorder

Raspberry Pi Pico 2 W running MicroPython
Electret mic, amplified by one…

View on GitHub

How I Built It

Parts used for the recorder:

Raspberry Pi Pico 2 W running MicroPython
An electret mic capsule I found in my parts box
A 2N2222 transistor as a one-stage amplifier (2.2k mic bias, 4.7k collector, 470k feedback, 1 µF coupling cap)
One push button, the onboard LED, a power bank

It records at 8 kHz and stores each note as 8-bit µ-law, which keeps about 14 bits' worth of dynamic range in half the space. The Pico has roughly 5 minutes of storage, and a note can be up to 30 seconds (it has to fit in RAM before saving). Each note is logged with the seconds since power-on, so the journal can say "12 minutes in" even though the Pico has no clock.

It was exam week and nothing could be ordered in time (5-day delivery), so everything is built from what I already had, plus one 1 µF capacitor from a local shop.

Getting the recording right was the hardest part. Initial readings capped out at a few milivolts, which meant my voice was drowned by the electrical noise. The 2N2222 helped fix that.
The noise was still bothering me a lot.

This is a comparision with different power inputs. Notice all that static noise? That mean't that barely anything i was saying was getting through. Whisper needed quiter audio. Luckily, the Raspberry has a modulated 3v3 output, which reduced the noise by half, enough for the models.

Ollama setup with gemma4 was quite easy. It is whats used for transcribing. The user gets the option to choose between models they have installed. The app autodetects new models pulled by ollama. Whisper also provides the same options-The user can choose which model they want for maximum clarity.
The model is responsible for interpreting the data from whisper, generating tips, weekly blog, and figuring out if the data from SerpAPI is good enough to touch grass.

There is also a SerpAI integration for periodic weather checks. A bit of motivation to "Touch grass" when it detects the weather is good. User can use their Pincode or city to set the location.

Why Does Open Innovation Matter?

A diary is about the most private thing you can write. Your thoughts, where you went, how you felt, in your own voice. With open models running locally, none of it leaves my laptop. I wouldn't want to send voice recordings of my walks to a company's server, and with this setup I don't have to.

It works offline and costs nothing. No API key, no subscription, no usage limits. After the one-time model download, it runs with Wi-Fi off.
Only thing needing wifi is the weather alarm, which is optional.

I can pick the model that fits. On my laptop (32 GB RAM, no dedicated GPU), I switch between Gemma 4 E2B, E4B and the 26B mixture-of-experts model from a dropdown, trading speed against writing quality. With a closed API, that choice isn't mine.

It's mine to change. I can rewrite the prompt, swap Whisper sizes, or (next) fine-tune a model on my own entries so it writes the way I do. None of that requires anyone's permission.

Trying it out

Got a lot of looks walking around with whats essetially a recorder without bodywork, I sucessfully took a couple tours of the campus and some tests in my room.
A video of me using it around campus

Prize Categories

Best Use of Gemma - Its the backbone of the project. Every decision is taken by this model.
Best Use of SerpApi - Thought I could sneak this in, with my weather report.

They demanded a picture

Aryan Garg — Mon, 05 Oct 2026 04:12:41 +0000

This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend

What I Built

We built a local upscaler! My friends love looking at pictures. But as the screens increase in resolution, the picture starts...fading away. Imagine that, a digital album fading away like an old picturebook. particularly the faces, which become really blurry.

Upscaling is a popular technology, using AI to recreate the edges and lines to make the image sharper. Most existing tools require the customer to send images over to a random website, something my friends didn't want to do with their photogaphs.

drumroll....ENTER LOCAL LLMS

Demo

Code

DhritiGupta2006 / They-demanded-a-picture

Revive

Revive makes old family photos sharper, gently fixes blurry faces, and writes a short caption for each one When it's done, you get a little photo album you can open on any computer, even without internet.

Your photos stay on this computer. Nothing is uploaded anywhere. After the one-time setup, Revive works with the internet switched off.

Setting it up (once)

You need two free programs first:

Python: download it from python.org/downloads and install it. On Windows, tick the box that says "Add python.exe to PATH" on the first screen of the installer.
Ollama: download it from ollama.com/download and install it. This is what lets Revive write captions on your own computer.

Then set up Revive itself:

Windows: open the scripts folder and double-click setup.bat.
Mac: open the scripts folder and double-click Setup Revive.command. If your Mac says it can't be opened, right-click it, choose…

View on GitHub

How I Built It

Revive is a fast API server with a simple HTML/CSS/JS landing page. It literally has no build steps, less to break on other systems.
This is specialised for faces, which is the most we could do in the 24 hours we had.

Processing order

GFPGAN v1.4 at original size --> Real-ESRGAN(2x) --> gemma4(via ollama)

This doesn't need a GPU either! so any laptop device can use this program to revive their photos on the fly :D

We focused on intuitivity, using established typography rules, and easy to undestand exit codes and error messages, this software can be used by anyone

Faces that look like themselves

Meticulous testing was done to make the faces look as close as possible to the orignal, tinkering with GFPGAN's weight values to avoid airbrushing and glassing was an excercise in endurance.

Offline

The primary requirement, everyone was against sending data out, so we brought the software in.

Why Does Open Innovation Matter?

Open models were the only way to build what they wanted.

Nothing leaves the computer

Its offline, there isn't even any bit of code that sends anything online

Works anytime

No internet, no condition, no firewalls, just your photos and the tool

Customizable!!

We made it, we can change it. Open source ftw

Prize Categories

Best use of gemma - Gemma4-e4b runs locally and is the brain here, it writes captions and makes the albums.

DEV Community: Aryan Garg

A file manager for the lazy

What I Built

Demo

Code

AryanGarg-beep / sloth

sloth 🦥

Why

How I Built It

Why Does Open Innovation Matter?

The Lazy Payoff

Prize Categories

Field Notes IRL. Touch the grass!

What I Built

Code

AryanGarg-beep / touch-grass

Field Notes: a pocket voice recorder (Pico 2 W) and an offline journal app (Whisper + Gemma)

Field Notes

What's here

The recorder

How I Built It

Why Does Open Innovation Matter?

Trying it out

Prize Categories

They demanded a picture

What I Built

Demo

Code

DhritiGupta2006 / They-demanded-a-picture

Revive

Setting it up (once)

How I Built It

Processing order

Faces that look like themselves

Offline

Why Does Open Innovation Matter?

Nothing leaves the computer

Works anytime

Customizable!!

Prize Categories

Did they like it??

YES!!!

Built by