DEV Community: Rachana Yadav

DEV account connection not recognized

Rachana Yadav — Wed, 07 Oct 2026 06:17:02 +0000

Hi! I'm participating in Hacktoberfest 2026 Week 1: Touch Grass.

My DEV account is already connected to my MLH account. In DEV Settings → Account, I can see MLH connected, and the email addresses match.

However, my Hacktoberfest participant dashboard still shows “Connect DEV account” as incomplete. Clicking the button only takes me to DEV Account Settings, where the MLH connection is already present.

My DEV username is @yadavrachana458.

Could someone please check why the Hacktoberfest dashboard is not recognizing the connection?

Thank you!

TouchGrass AI — An Open-Source AI Outdoor Challenge Generator 🌿

Rachana Yadav — Wed, 07 Oct 2026 05:38:27 +0000

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

What I Built

I built TouchGrass AI, a web application that uses open-weight AI to encourage people to step away from their screens and spend time outdoors.

Users choose an outdoor activity, how much time they have, and their current mood. TouchGrass AI then generates a short personalized outdoor challenge.

For example, users can choose:

🚶 Walking
🏃 Running
🌱 Gardening
🐦 Bird watching
🥾 Hiking
📸 Outdoor photography

The goal is simple: instead of using AI to keep people on a screen, use AI to give them a reason to leave the screen and go outside. 🌿

The project is designed for anyone who wants a simple push to spend more time outdoors.

Demo

GitHub repository:
[https://github.com/rachana458/Touchgrass-ai]

Code

GitHub:
[https://github.com/rachana458/Touchgrass-ai]

The repository contains the complete Next.js application, including the AI integration and user interface.

How I Built It

I built TouchGrass AI with:

Next.js
React
TypeScript
Tailwind CSS
Transformers.js
Qwen2.5-0.5B-Instruct

The AI component uses the open-weight Qwen2.5-0.5B-Instruct model through Transformers.js.

The application sends the user's selected activity, available time, and mood to the model and asks it to generate one short outdoor activity idea.

I then use the generated idea inside a structured challenge:

Start with a few minutes of gentle movement.
Follow the AI-generated outdoor activity.
Finish by enjoying the outdoors.

I intentionally kept the AI output short because smaller open-weight models can produce unpredictable results when asked to generate long structured responses.

The application therefore uses the AI for the creative part while the application controls the final structure.

Why Does Open Innovation Matter?

Open innovation makes experimentation with AI much more accessible.

For this project, I was able to experiment with an open-weight model instead of depending on a paid proprietary AI API.

Using Transformers.js also allowed me to explore running the model directly in the web application.

This makes it possible to build small AI experiences without requiring a separate paid AI service for every generation.

More importantly, open AI tools give developers the freedom to experiment with ideas that might otherwise be difficult or expensive to prototype.

For TouchGrass AI, that made it possible to explore a simple question:

Can we use AI to encourage people to spend less time with technology?

My Agent Session

I did not use DevRelay for this project, so I am leaving this optional section out.

Prize Categories

I am submitting TouchGrass AI for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass.

Hacktoberfest Weekend Challenge: Build for a Friend — SpeakMate AI

Rachana Yadav — Sat, 03 Oct 2026 07:25:04 +0000

# 🤖 SpeakMate AI: An AI English Practice Companion I Built for a Friend

Learning a language is not only about knowing the rules. You need a place where you can actually practice, make mistakes, and understand why an answer is correct.

One of my friends is learning English, and I wanted to build something specifically around that problem.

For the Hacktoberfest 2026 Weekend Challenge, I built SpeakMate AI — a focused English practice companion for a real friend.

## 🎯 The Problem

My friend needed a simple way to practice English regularly.

A general chatbot can answer questions, but I wanted to build something more focused.

Instead of simply chatting with an AI, SpeakMate gives the learner actual exercises:

Grammar questions
Vocabulary practice
Sentence correction
Multiple-choice answers
Immediate explanations
Difficulty levels

The goal was simple:

Don't just talk to the learner. Give them something to practice.

## 💡 What I Built

SpeakMate AI has three main practice modes.

### 📝 Grammar Practice

The learner chooses a difficulty level:

Beginner
Intermediate
Advanced

The AI generates a grammar exercise with multiple-choice answers.

After answering, the learner gets:

The correct answer
Whether their answer was correct
A grammar explanation
A running score

### 📚 Vocabulary Practice

The vocabulary mode introduces words with:

Meaning
Example sentence
Multiple-choice question
Answer checking
Explanation

This makes vocabulary learning more interactive than simply reading a list of words.

### ✍️ Sentence Correction

The learner receives an incorrect English sentence.

They then choose which option correctly fixes the sentence.

After checking the answer, SpeakMate explains the grammar mistake.

## 🧠 The AI Behind SpeakMate

One of the most important parts of this project is that the AI is not just a remote API call.

I used:

Transformers.js
WebGPU
Qwen2.5-0.5B-Instruct
Next.js
TypeScript
Tailwind CSS

The model runs in the browser using Transformers.js and WebGPU.

This means the project can experiment with local inference rather than depending entirely on a paid hosted AI API.

The open approach also makes the AI layer easier to experiment with: the model and inference setup can evolve as the project evolves.

## 🌱 Why Open Innovation Matters Here

For this project, using an open/open-weight model and local inference was important because I wanted the learning tool to be lightweight and inexpensive to experiment with.

A learning companion shouldn't necessarily require a paid AI service every time someone wants to practice a grammar question.

Running the model locally also gives the project more control over how the AI component is used and makes it possible to experiment with different models and configurations.

That was one of the biggest things I wanted to explore through this challenge.

## 🏗️ How It Works

The basic flow is:

Choose Practice Mode
↓
Choose Difficulty
↓
Local AI Model
↓
Generate Exercise
↓
Answer Question
↓
Check Answer
↓
Explanation + Score

### SpeakMate AI Homepage

### Grammar Practice

### Vocabulary Practice

### Sentence-correction Practice

## 🛠️ Tech Stack

Technology	Purpose
Next.js	Web application
TypeScript	Application development
Tailwind CSS	UI
Transformers.js	Running the AI model
WebGPU	Browser acceleration
Qwen2.5	Language model

## 🔗 Project

The complete source code for SpeakMate AI is available on GitHub:

View the SpeakMate AI source code on GitHub

You can clone it and run it locally with:

npm install
npm run dev

Then open:
the link

A browser with WebGPU support is recommended for the local AI model.

## ❤️ What I Learned

Building SpeakMate taught me that a useful AI project doesn't have to be a huge application.

The most important part was starting with a real person's problem and building around that problem.

I also learned more about:

Running AI models in the browser
Transformers.js
WebGPU
Prompt design
Parsing AI-generated output
Building interactive learning experiences with Next.js

## 🚀 What's Next

There are several things I would like to add in the future:

Learning progress history
More question types
Listening practice
Pronunciation practice
More vocabulary categories
Better question diversity
Support for additional local AI models

For this weekend, however, the goal was simple:

Build something useful for one real person.

And that's what SpeakMate AI is.

Built for the Hacktoberfest 2026 Weekend Challenge — Build for a Friend.

#devchallenge #weekendchallenge #hf26challenge

Hi, i am new to the community.

Rachana Yadav — Fri, 02 Oct 2026 10:15:54 +0000