DEV Community: Adya Srivastava

LazyDay AI: Less Overthinking, More Tiny Wins — A Slow & Steady Approach to Productivity

Adya Srivastava — Tue, 20 Oct 2026 18:05:58 +0000

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

What I Built

🦥 LazyDay AI — Do less. Stress less. Move forward, one tiny step at a time.

Ever opened your to-do list, seen 20 tasks staring back at you, and decided that maybe tomorrow would be a better day to start?

Same problem, different day.

That's why I built LazyDay AI, a lightweight productivity website designed around the idea that productivity shouldn't always mean doing more. Sometimes, it means making the next step so small that getting started feels easy.

Here's what it does:

📝 Brain Dump: Put every task and thought in one place without worrying about organizing them.
🔋 Energy-Based Planning: Choose your current energy level and create a more manageable plan.
🎯 Tiny Tasks: Turn an overwhelming list into smaller actions.
✅ Progress Tracking: Check off completed tasks and see your progress.
🌿 Distraction-Free Design: A calm, responsive interface that keeps things simple.

The people who benefit? Students, procrastinators, overwhelmed planners, and anyone who wants to get things done without turning every day into a productivity competition.

The philosophy: You don't need to finish everything today. You just need a next step.

Demo

🚀 Try LazyDay AI here:

👉 https://adya-srivastava16.github.io/LazyDay-AI/

Open the website, dump your tasks, choose your energy level, and let the planner help you get started.

Code

💻 Explore the GitHub repository:

👉 LazyDay AI on GitHub

Built with HTML, CSS, and JavaScript, the current version runs directly in your browser.

How I Built It

I built LazyDay AI using three core web technologies:

HTML5 for the structure and content.
CSS3 for the clean interface, responsive layouts, and animations.
JavaScript for task organization, energy selection, task completion, and progress tracking.

The current version uses lightweight, rule-based planning logic to demonstrate the experience without requiring a server or API key.

An important distinction: a live open-weight AI model is not integrated into this version yet. Integrating an open model to understand natural-language brain dumps and generate personalized, energy-aware plans is a planned next step.

I wanted to start with a simple, usable prototype rather than overcomplicate the first version. The project provides a foundation for experimenting with open-source AI while keeping the interface accessible.

Why Does Open Innovation Matter?

Open innovation makes it possible for developers to experiment, learn from shared knowledge, and improve ideas without having to build every component from scratch.

For a project like LazyDay AI, this matters in three ways:

1. Accessibility

Simple tools built with open web technologies are easy to run, inspect, and extend. Developers can experiment without needing an expensive infrastructure setup.

2. Freedom to experiment

An eventual open-weight model integration could let developers explore different planning approaches, customize prompts, and compare models rather than relying entirely on a closed API.

3. Privacy and control

With a suitably licensed model running locally, future versions could potentially process personal task lists without sending them to a third-party inference service. That would depend on the actual implementation.

Open innovation doesn't automatically make a product better. It gives us more opportunities to understand, modify, and improve how it works.

For me, that's the exciting part: starting with a small idea and leaving room for the community to make it better.

My Agent Session

I don't have a DevRelay session link to share for this submission. If I create and save one, I'll add it here.

The Lazy Payoff

The biggest payoff is reducing the effort required to get started.

Instead of spending extra time figuring out how to organize a long to-do list, users can put their tasks in one place, select their energy level, and get a starting plan.

I haven't measured a verified time-saving figure yet, so I won't invent one. The goal is to reduce planning friction, make tasks feel more approachable, and help users take one small step instead of postponing everything.

Because sometimes the most productive thing you can do is make productivity easier.

Prize Categories

Primary challenge: Hacktoberfest Open-Source AI Challenge — Week 3: Slow and Steady.

I'll only claim additional partner categories if the project meets their specific requirements.

🦥 One last thing

LazyDay AI isn't about being lazy forever. It's about making progress without unnecessary pressure.

Less overwhelm. Smaller steps. Steady progress.

Built by Adya Srivastava for the Slow and Steady challenge.

LazyDay AI: Less Overthinking, More Tiny Wins — A Slow & Steady Approach to Productivity

Adya Srivastava — Tue, 20 Oct 2026 17:53:50 +0000

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

What I Built

🦥 LazyDay AI — Do less. Stress less. Move forward, one tiny step at a time.

Ever opened your to-do list, seen 20 tasks staring back at you, and decided that maybe tomorrow would be a better day to start?

Same problem, different day.

Here's what it does:

📝 Brain Dump: Put every task and thought in one place without worrying about organizing them.
🔋 Energy-Based Planning: Choose your current energy level and create a more manageable plan.
🎯 Tiny Tasks: Turn an overwhelming list into smaller actions.
✅ Progress Tracking: Check off completed tasks and see your progress.
🌿 Distraction-Free Design: A calm, responsive interface that keeps things simple.

The people who benefit? Students, procrastinators, overwhelmed planners, and anyone who wants to get things done without turning every day into a productivity competition.

The philosophy: You don't need to finish everything today. You just need a next step.

Demo

🚀 Try LazyDay AI here:

👉 https://adya-srivastava16.github.io/LazyDay-AI/

Open the website, dump your tasks, choose your energy level, and let the planner help you get started.

Code

💻 Explore the GitHub repository:

👉 LazyDay AI on GitHub

Built with HTML, CSS, and JavaScript, the current version runs directly in your browser.

How I Built It

I built LazyDay AI using three core web technologies:

HTML5 for the structure and content.
CSS3 for the clean interface, responsive layouts, and animations.
JavaScript for task organization, energy selection, task completion, and progress tracking.

The current version uses lightweight, rule-based planning logic to demonstrate the experience without requiring a server or API key.

Why Does Open Innovation Matter?

Open innovation makes it possible for developers to experiment, learn from shared knowledge, and improve ideas without having to build every component from scratch.

For a project like LazyDay AI, this matters in three ways:

1. Accessibility

Simple tools built with open web technologies are easy to run, inspect, and extend. Developers can experiment without needing an expensive infrastructure setup.

2. Freedom to experiment

An eventual open-weight model integration could let developers explore different planning approaches, customize prompts, and compare models rather than relying entirely on a closed API.

3. Privacy and control

Open innovation doesn't automatically make a product better. It gives us more opportunities to understand, modify, and improve how it works.

For me, that's the exciting part: starting with a small idea and leaving room for the community to make it better.

My Agent Session

I don't have a DevRelay session link to share for this submission. If I create and save one, I'll add it here.

The Lazy Payoff

The biggest payoff is reducing the effort required to get started.

Instead of spending extra time figuring out how to organize a long to-do list, users can put their tasks in one place, select their energy level, and get a starting plan.

Because sometimes the most productive thing you can do is make productivity easier.

Prize Categories

Primary challenge: Hacktoberfest Open-Source AI Challenge — Week 3: Slow and Steady.

I'll only claim additional partner categories if the project meets their specific requirements.

🦥 One last thing

LazyDay AI isn't about being lazy forever. It's about making progress without unnecessary pressure.

Less overwhelm. Smaller steps. Steady progress.

Built by Adya Srivastava for the Slow and Steady challenge.

LittleListing: Turning Open-Source AI into a Side Hustle

Adya Srivastava — Thu, 15 Oct 2026 09:20:46 +0000

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

LittleListing: Your AI-Powered Marketplace Listing Studio ✨

What I Built

Meet LittleListing — AI Listing Studio, a lightweight AI-powered tool designed to help small businesses and independent creators turn product details into compelling, marketplace-ready listings.

Writing product descriptions, finding the right keywords, and creating attractive titles can take valuable time, especially for people running a small side hustle. LittleListing makes this process easier by helping users generate:

Product titles that are clear and appealing.
Product descriptions tailored to the intended audience.
Search tags and keywords to help make listings more discoverable.
Brand-aligned content with different tones of voice.
Platform-oriented listings for marketplaces and online selling channels.

🎯 Who is it for?

LittleListing is built for independent makers, freelancers, Etsy sellers, small business owners, and anyone who wants to sell products online without spending hours writing listing copy.

The side-hustle opportunity: Sellers could use a tool like LittleListing to save time on repetitive writing, maintain consistent product descriptions, and focus more on creating and selling their products.

My goal is to make AI-powered content creation more accessible, customizable, and privacy-conscious through open-source AI.

Demo

Try LittleListing live:

👉 LittleListing — AI Listing Studio

Explore the interface, enter product details, choose your preferences, and see how the tool helps turn product information into listing content.

Code

GitHub Repository:

Adya-Srivastava16/LittleListing-AI

The project uses a simple web stack, making it approachable for developers who want to explore, improve, and extend the application.

I built LittleListing as a practical experiment in using open-source AI to solve a real problem for people building small online businesses.

How I Built It

I built LittleListing using HTML, CSS, JavaScript, and Ollama for local AI inference.

The application combines a straightforward browser-based interface with AI-assisted listing generation.

The main technologies:

HTML — structures the application and its input forms.
CSS — provides the visual design and responsive layout.
JavaScript — handles user input, generation workflows, previews, and copy-to-clipboard interactions.
Ollama — provides a way to run compatible language models locally.
Llama 3.2 — the open-weight model used in my local inference setup.

The intended local AI workflow uses Ollama to generate listing content from the product details supplied by the user. A preview mode also makes it possible to explore the interface without relying on a running model.

I focused on keeping the project lightweight and easy to run, without requiring a complicated backend or a paid AI API as part of the local inference workflow.

Why Does Open Innovation Matter?

Open innovation is important because powerful AI tools should not be accessible only to companies with large budgets or developers who can afford ongoing API costs.

For a small seller, every recurring expense matters. Open-weight models and tools such as Ollama create opportunities to experiment with AI while retaining more control over the technology.

With LittleListing, open innovation makes it possible to explore:

More control: Developers can experiment with compatible models and customize prompts.
Privacy-conscious workflows: With local inference configured, product information can be processed on the user's own machine rather than sent to a third-party AI API.
Lower recurring costs: Local inference can avoid per-request API charges, although hardware and electricity still have costs.
Flexibility: The generation workflow can be adapted to different products, audiences, and writing styles.
Accessibility: A simple web interface makes the idea approachable for non-technical sellers.

What excites me most is the possibility of building useful AI-powered tools without making them dependent on a single closed provider.

LittleListing is my small step toward making open AI practical for everyday side hustles.

What I Learned

Building LittleListing helped me explore how a simple web application can become more useful when combined with open-weight AI.

It also made me think beyond generating text: a helpful AI product needs a clear user experience, useful outputs, practical setup instructions, and a real problem to solve.

My next goal is to gather feedback from actual sellers and improve the generated listings based on their needs.

What's Next?

Some improvements I would like to explore include:

More customizable listing templates.
Better keyword and search-tag suggestions.
Additional marketplace-specific formatting.
Exporting generated listings.
User feedback and quality evaluation.
More model options and improved local inference setup.

I'd love to hear suggestions from other developers and small-business owners!

Final Thoughts

LittleListing started with a simple question:

What if small sellers could spend less time writing listings and more time building their businesses?

By combining a lightweight web interface with open-source AI tooling, I'm exploring one possible answer.

Thanks for checking out my submission! If you find the project interesting, give the repository a , try the live demo, or share an idea that could make it more useful.

Live Demo: https://adya-srivastava16.github.io/LittleListing-AI/

GitHub: https://github.com/Adya-Srivastava16/LittleListing-AI

Hacktoberfest #OpenSource #AI #SideHustle #Ollama #WebDev

Trail Buddy: An Open-Source AI Field Guide for Getting Outside

Adya Srivastava — Sun, 11 Oct 2026 12:59:14 +0000

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

What I Built

I built Trail Buddy, a small web app for people who want to notice more on a walk. Describe something you saw or heard—a bird call, a changing leaf, a patch of moss—and it finds the closest match in a pocket-sized nature guide. It also offers simple prompts to encourage looking, listening, and exploring outdoors.

The app is designed to make the screen a quick stop: write a note, get a starting point, and look up at the world again. Matches are suggestions, not definitive species identifications.

Demo

Try the live app: Trail Buddy

Code

Explore the source: Trail Buddy on GitHub

How I Built It

Trail Buddy is built with HTML, CSS, and JavaScript. It uses Transformers.js to run the open-weight MiniLM sentence embedding model in the browser.

When someone submits an observation, the model turns it and each field-guide note into an embedding. The app compares them with cosine similarity and shows the closest match. The journal is stored in the browser’s local storage.

The first model load needs an internet connection to download the library and model. After that, inference happens in the browser; this version doesn’t guarantee fully offline use.

Why Does Open Innovation Matter?

Using an open-weight model lets Trail Buddy run inference in the visitor’s browser without sending their observation to a hosted AI API. That means no inference API key, no app server handling personal field notes, and no per-request model bill.

The approach is also easy to inspect and adapt. I can change the field-guide notes, try another embedding model, or adjust the matching logic without depending on a closed model provider. For this project, that flexibility and local processing fit the goal: a simple, private nudge to go explore.

Prize Categories

I’m not entering a partner category; Trail Buddy doesn’t currently use the listed partner technologies.