DEV Community: jay Maan

Weekly coding challenge

jay Maan — Tue, 20 Oct 2026 09:34:31 +0000

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

What I Built

Demo

Code

How I Built It

Why Does Open Innovation Matter?

My Agent Session

The Lazy Payoff

Prize Categories

Weekly challeneg

jay Maan — Tue, 13 Oct 2026 09:23:13 +0000

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle

What I Built

Demo

Code

How I Built It

Why Does Open Innovation Matter?

My Agent Session

My First User

Prize Categories

Dev week 1

jay Maan — Tue, 06 Oct 2026 17:46:57 +0000

*This is a submission for the
An AI-powered outdoor activity generator. The user enters their mood, available time, and whether they're alone or with friends, and the app suggests a simple offline activity.

What I Built

I built TouchGrass AI, a lightweight open-source AI-powered web app that helps people step away from their screens and spend time outdoors.
Users enter their mood, available time, and preferred activity type, and the app generates practical outdoor activity ideas. The goal is simple: use technology to encourage people to put their phones down and experience the real world.
The project is designed for students, families, and anyone looking for simple ways to spend more time outside.

Demo

Live Demo: https://touchgrass-ai-demo.vercel.app
Demo description: TouchGrass AI lets users choose their mood, available time, and company, then generates a simple outdoor mission designed to encourage them to step away from their screen and explore the real world.

Code

<!DOCTYPE html>

TouchGrass AI
 * { box-sizing: border-box; } <div class="highlight"><pre class="highlight plaintext"><code>body { margin: 0; font-family: Arial, sans-serif; background: #f4f7f2; color: #1f3024; } .container { max-width: 700px; margin: auto; padding: 40px 20px; } h1 { font-size: 42px; margin-bottom: 10px; } .subtitle { font-size: 18px; line-height: 1.6; } .card { background: white; padding: 25px; margin-top: 25px; border-radius: 18px; box-shadow: 0 5px 20px rgba(0,0,0,.08); } label { display: block; margin-top: 18px; margin-bottom: 7px; font-weight: bold; } select, button { width: 100%; padding: 13px; border-radius: 10px; border: 1px solid #ccc; font-size: 16px; } button { margin-top: 25px; cursor: pointer; background: #2f6b3c; color: white; border: none; font-weight: bold; } button:hover { opacity: .9; } #result { margin-top: 25px; padding: 20px; border-radius: 12px; background: #eef6ed; line-height: 1.6; display: none; } </code></pre></div>

🌱 TouchGrass AI

<p class="subtitle">
  A tiny AI-inspired activity generator that turns screen time
  into real-world time.
</p>

<div class="card">
  <label for="mood">How are you feeling?</label>
  <select id="mood">
    <option>Energetic</option>
    <option>Relaxed</option>
    <option>Bored</option>
    <option>Stressed</option>
    <option>Curious</option>
  </select>

  <label for="time">How much time do you have?</label>
  <select id="time">
    <option>10 minutes</option>
    <option>30 minutes</option>
    <option>1 hour</option>
    <option>2+ hours</option>
  </select>

  <label for="company">Who are you with?</label>
  <select id="company">
    <option>Alone</option>
    <option>Friends</option>
    <option>Family</option>
  </select>

  <button onclick="generateActivity()">
    🌿 Give Me an Outdoor Mission
  </button>

  <div id="result"></div>
</div>

demo

How I Built it

I built TouchGrass AI with HTML, CSS, and JavaScript. It uses user preferences to generate simple outdoor activities and encourage users to spend less time on screens.

Prize Categories

Open-Source AI / AI Innovation — select the specific category only if the project meets that category's requirements.

Voice to recipe

jay Maan — Sun, 04 Oct 2026 07:41:56 +0000

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

What I Built

Demo

• it runs locally via the

terminal.

Code

import os
from faster_whisper import WhisperModel
import requests
import json

# 1. LOCAL TRANSCRIPTION (Whisper)
def transcribe_audio(audio_path):
    print("Transcribing audio locally...")
    model = WhisperModel("base", device="cpu", compute_type="int8")
    segments, info = model.transcribe(audio_path, beam_size=5)

    transcript = " ".join([segment.text for segment in segments])
    return transcript

# 2. LOCAL AI PROCESSING (Ollama + Llama 3)
def structure_recipe(raw_transcript):
    print("Structuring recipe with local Llama 3...")
    url = "http://localhost:11434/api/generate"

    system_prompt = (
        "You are a helpful culinary archivist. Your job is to take a messy, conversational "
        "audio transcript from a grandparent and turn it into a beautifully structured recipe. "
        "Extract the Title, a brief heartwarming description, Ingredients with measurements, "
        "and Step-by-Step Instructions. Do not add any conversational filler in your final response."
    )

    payload = {
        "model": "llama3",
        "prompt": f"{system_prompt}\n\nTranscript: {raw_transcript}",
        "stream": False
    }

    response = requests.post(url, json=payload)
    return response.json()['response']

# 3. RUN THE PIPELINE
if __name__ == "__main__":
    audio_file = "grandpas_spaghetti_story.mp3" 

    if os.path.exists(audio_file):
        raw_text = transcribe_audio(audio_file)
        final_recipe = structure_recipe(raw_text)

        with open("heirloom_recipe.md", "w") as f:
            f.write(final_recipe)
        print("Success! Your structured recipe is ready in heirloom_recipe.md")
    else:
        print(f"Please place an audio file named '{audio_file}' in this directory.")

How I Built It

• the Voice-to-Recipe Heirloom Kit for Grandpa Joe to preserve his family cooking stories entirely offline.

Why Does Open Innovation Matter?

• open-weight local models keep personal family stories 100% private and run completely free forever without cloud API costs.

My Agent Session

Prize Categories

Weekly coding

jay Maan — Sun, 04 Oct 2026 07:36:08 +0000

Code

import os
from faster_whisper import WhisperModel
import requests
import json

# 1. LOCAL TRANSCRIPTION (Whisper)
def transcribe_audio(audio_path):
    print("Transcribing audio locally...")
    model = WhisperModel("base", device="cpu", compute_type="int8")
    segments, info = model.transcribe(audio_path, beam_size=5)

    transcript = " ".join([segment.text for segment in segments])
    return transcript

# 2. LOCAL AI PROCESSING (Ollama + Llama 3)
def structure_recipe(raw_transcript):
    print("Structuring recipe with local Llama 3...")
    url = "http://localhost:11434/api/generate"

    system_prompt = (
        "You are a helpful culinary archivist. Your job is to take a messy, conversational "
        "audio transcript from a grandparent and turn it into a beautifully structured recipe. "
        "Extract the Title, a brief heartwarming description, Ingredients with measurements, "
        "and Step-by-Step Instructions. Do not add any conversational filler in your final response."
    )

    payload = {
        "model": "llama3",
        "prompt": f"{system_prompt}\n\nTranscript: {raw_transcript}",
        "stream": False
    }

    response = requests.post(url, json=payload)
    return response.json()['response']

# 3. RUN THE PIPELINE
if __name__ == "__main__":
    audio_file = "grandpas_spaghetti_story.mp3" 

    if os.path.exists(audio_file):
        raw_text = transcribe_audio(audio_file)
        final_recipe = structure_recipe(raw_text)

        with open("heirloom_recipe.md", "w") as f:
            f.write(final_recipe)
        print("Success! Your structured recipe is ready in heirloom_recipe.md")
    else:
        print(f"Please place an audio file named '{audio_file}' in this directory.")