DEV Community: Tanmay Sharma

Hactoberfest - 2026-3

Tanmay Sharma — Sun, 25 Oct 2026 15:04:31 +0000

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

** My First Hacktoberfest Project: A Text Summarizer with Llama 3

Hello People! 👋

I'm new to this whole open-source and Hacktoberfest thing, but I wanted put something there so here, I built for Week 3. I'm sure there are things I could do better, and I'm totally okay to feedback and learning from this experience. So let's do this.

My idea

You know that feeling when you find an interesting article but it's super long, and you just want the main points? Yeah, me too. I thought: "What if I could build something that automatically shortens text for me?"

So for Hacktoberfest, I decided to create a "Text Summarizer" that does exactly that.

What I Built

It's a simple web app where one:

Copy and paste any text (article, document, whatever)
Choose how short or long one wants the summary
Click a button
Get a nice summary back

That's it! No complicated setup, no fancy algorithms I invented myself. Just using Llama 3 (a really good open-source AI model) to do the summarizing.

How It Works (Really Simply)

I used:

Llama 3 - An AI model that's free and open-source (made by Meta)
Ollama - A tool that lets you run Llama 3 on your own computer
HTML, CSS, JavaScript - For the web interface (the pretty part you see)
Python Flask - For the backend (optional, but it works better with it)

User run Ollama locally, which means your text stays on the computer. Nothing goes to the cloud. Privacy-friendly!

Why I Built This for Hacktoberfest

Hacktoberfest 2026 is all about open-source AI, and I really liked that idea. Everything in my project uses free, open-source tools:

Llama 3 is open-source ✅
Ollama is open-source ✅
Flask is open-source ✅
My code is open-source ✅

No paid APIs. No closed-source models. Just open tools helping each other.

The Honest Part

I'm not a super experienced developer. I'm learning as I go. This is my first real Hacktoberfest project, and I'm sure there are bugs, things I could optimize, or better ways to do stuff that I don't know about yet.

But I suppose that's okay! The point was to:

Build something useful
Learn how to work with AI models
Contribute something to open source
Maybe help someone else save time reading long texts

If you have suggestions or see something wrong, please let me know. I genuinely want to learn from this.

How to Use It

If you want to try it:

Get Ollama from https://ollama.ai
Run this command:

   ollama run llama3

Download my files from GitHub and open text_summarizer.html in your browser
Copy any text you want summarized
Click the button and see the magic happen!

It'll take a bit to download the Llama 3 model (about 4.7 GB), but after that it's really fast.

What I Learned

Building this taught me:

How AI models like Llama 3 actually work (kind of!)
How to use APIs in JavaScript
How to build something with Python backend and JavaScript frontend
That open-source tools are really powerful and accessible

What's Next?

I've shared the basic version, but there are SO many things that could be added:

Summarizing directly from URLs
Saving summaries to a file
Different languages
More customization options
Performance improvements

Maybe in the future, or maybe someone reading this will have cool ideas!

Thanks

Thanks to:

The Llama 3 team for creating such an amazing model
The Ollama team for making it easy to run locally
Hacktoberfest for organizing this and encouraging open-source work
Everyone on DEV.to who writes great content (your articles inspired me!)

Find the Code

Everything is on GitHub (link here), and I'd love if you:

Try it out
Give feedback
Suggest improvements
Fork it and make it better!

Final Thought

I'm realizing that building something and sharing it is way better than waiting until it's "perfect." This probably isn't perfect, but it works, it's useful, and it's open source.

So, Kbai!

GitHub Repo:https://github.com/BlissfulSoup/Text-summariser-llama3-hactoberfest-2026-3-

Title: Touch Grass Check: an AI that makes sure you went outside

Tanmay Sharma — Sat, 10 Oct 2026 10:49:19 +0000

This is my first Hacktoberfest project. The week-one theme was "touch grass", so I built a small web app that checks whether you really went outside.

---How it works----

Take or upload a photo.
An open-source AI model (CLIP, running in your browser with Transformers.js) decides whether the photo is outdoors in nature.
If it is, One get "Touch grass: confirmed"(loved writing that) . If not, you're sent back outside.
The AI then names the plant from a list of 126 common plants, flowers and trees. Wikipedia supplies the origin and description.
One can copy the result, download it as a .txt file, or save it as a PDF.

The photo never leaves the device. The model runs locally, and only the plant name is sent to Wikipedia.

-----What I learned----

AI models can run directly in a web page, with no server or API key.
The first visit downloads the model, so it's slow once, then faster.
It isn't perfect. It was too strict about a close-up stock photo of a rose, but it passed a real photo of grass from my street. It only knows the plants on its list.

Next steps? more plants, a gallery of past nature notes, and a daily outdoor challenge. But a break is a must (my exams are over for now)

I built this with help from an AI assistant, and I tested it myself outdoors. If you try it, tell me what plant it found!

This wasn't built with the direct intention to replace/innovate but more as a step to learn something new and maybe motivate people to create/innovate in things.

And as always, thank you for entertaining my childish project, feedbacks are always appreciated.. Kbai

Shield for A friend

Tanmay Sharma — Sat, 03 Oct 2026 15:49:48 +0000

Well I'm new to this but..

Hi everyone Tanmay here,
I'm new to coding and stuff but am curious to learn so here I am.

This is uh my gift?(tease material honestly) for my Instagram addict friend.

Idea: A timer+warning system to limit social media usage & an in-built deep-work mode (passcode controlled)
Ps. This is made on html (no app sorry, I'm new to this... But maybe in future? Yes)

Anyway link below..
https://codepen.io/BlissfulSoup/pen/ogZGQLp

And um I'm open to suggestions&feedback and anyone who had advice so....
Kbai /ᐠ - ˕ -マ