This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady
What I Built
Meet EventEase — an event-planning web application designed to make organising events easier, faster, and less overwhelming.
From festive celebrations and birthdays to college events and personal gatherings, planning involves countless small decisions: schedules, budgets, activities, and checklists. EventEase aims to bring these planning tasks together in one place so users can spend less time organising and more time enjoying their events.
The idea is simple: less planning stress, more memorable celebrations.
Demo
🎥 Project Demo: https://youtu.be/mZEHeJul-1E?si=DI8OOtmH3rK9oIUd
🌐 Live Website: https://event-ease-gdk3.onrender.com
Project Updates & Community
I've also shared EventEase on LinkedIn, documenting my project and sharing my journey of building a solution to simplify event planning.
🔗 LinkedIn Post: https://lnkd.in/p/gwb3mGRF
Building in public is an important part of learning: sharing progress, receiving feedback, and continuously improving through community participation.
Code
💻 GitHub Repository: https://github.com/himanshisharma18-wq/Event_Ease
The project uses HTML, CSS, and JavaScript for the web interface, alongside its backend and AI-related components.
How I Built It
EventEase combines a web-based interface with an event-planning workflow to help users turn their ideas into actionable plans.
For the open-source AI direction, I am exploring the use of an open-weight language model through Ollama for local inference. This approach offers flexibility in model selection and the possibility of reducing reliance on proprietary AI APIs.
The specific model and integration should be described according to the implementation available in the repository.
Why Does Open Innovation Matter?
Open innovation gives developers more freedom to experiment, customise, and build technology around real-world needs.
For an event-planning application, local AI can offer useful advantages. Event details may include personal preferences, budgets, and locations. When inference runs locally, these details can remain on the user's machine instead of being sent to an external AI inference provider.
Open-weight models can also offer greater control over model selection and help reduce recurring API costs. Local inference still requires suitable hardware, and offline operation depends on having the model and necessary resources available locally.
For me, open innovation is about control, flexibility, and accessibility. Instead of depending entirely on a closed AI service, developers have more opportunities to experiment with different models and understand how the technology powering their applications works.
My Agent Session
An agent-session recording can be added here if available. This section is optional.
The Lazy Payoff
Event planning shouldn't feel like another full-time job.
EventEase aims to reduce repetitive planning work and help users move from an initial idea towards a structured event plan.
The goal is to make organising celebrations more approachable, reduce decision fatigue, and leave more time for the things that matter.
The best kind of automation is the kind that handles the tedious parts while leaving meaningful decisions to people.
Prize Categories
Hacktoberfest Open-Source AI Challenge — Week 3: Slow and Steady.
Additional partner categories should be included only if the project meets their eligibility requirements.
Building EventEase has been an opportunity to explore how web development and open-source AI can help simplify everyday tasks.
Build smarter. Plan simpler. Celebrate more. 🎉
Top comments (1)
Love the idea—event planning is the ultimate decision-fatigue machine.
Since you mentioned exploring Ollama for local inference, what's the actual pipeline for the AI part? Are you running a Node.js/Python backend to connect to Ollama, or handling it directly from the browser? Also, since budgets and locations are sensitive, keeping it local is a massive privacy win. Great submission for the "Slow and Steady" theme!