This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady
What I Built
One challenge many community members face is figuring out:
- Which events should I attend?
- Which communities match my interests?
- What should I do next to grow my skills or network?
- Where are the opportunities relevant to me?
Today, the answer usually involves browsing multiple community pages, Discord servers, Meetup groups, newsletters, social posts, and event platforms.
I built Community Compass, an AI-powered community and event discovery experience that reduces that effort.
Instead of asking members to manually search through dozens of opportunities, the platform analyzes their interests, goals, participation history, and community activity to surface:
- Recommended events
- Relevant communities
- Learning opportunities
- Volunteer roles
- Mentorship opportunities
- Personalized next-step suggestions
The goal is simple: let the AI do the searching so members can focus on participating.
This directly fits the "Slow and Steady" theme because it automates one of the most repetitive tasks in community building: discovering where you should spend your limited time and attention.
Demo
Screenshots
- Community Member Home
- Recommended Gatherings
- Suggested Communities
- Learning Goals
- Opportunity Recommendations
Code
GitHub Repository Pull Request:
https://github.com/HackerspaceMumbai/bethuya/pull/66
How I Built It
The project was designed as part of the Bethuya Community Operating System.
Architecture
- ASP.NET Core
- Blazor
- .NET Aspire
- Open-source AI models
- Local-first AI orchestration
- Community participation data
- Recommendation engine
AI Components
The recommendation experience is powered using open-source AI models rather than proprietary hosted-only services.
The AI helps:
- Understand member interests
- Categorize events
- Match opportunities to goals
- Generate recommendation summaries
- Surface relevant next actions
During development I used AI-assisted workflows and open-source AI tooling to rapidly iterate on user journeys and recommendation strategies.
The result is an experience where members no longer need to manually explore every community page or event listing to discover what's relevant to them.
Why Does Open Innovation Matter?
Open innovation was critical to this project.
Community organizations often operate with limited budgets and cannot afford expensive per-request AI APIs for every recommendation.
Using open-source AI provides several advantages:
Cost Control
Community platforms can run recommendation workloads without incurring significant API expenses.
Transparency
The recommendation logic can be inspected, improved, and adapted for community-specific needs.
Flexibility
Models can be replaced, fine-tuned, or augmented as requirements evolve.
Data Privacy
Community participation data does not need to be permanently shared with third-party providers.
Accessibility
Smaller local communities gain access to AI capabilities that would otherwise only be available to larger organizations with bigger budgets.
For a community-focused platform, openness is not just a technical preference. It is an enabler of sustainability and trust.
The Lazy Payoff
Without AI:
A member may need to:
- Browse multiple communities
- Check event listings individually
- Read event descriptions
- Compare schedules
- Evaluate relevance manually
With Community Compass:
The system proactively surfaces the most relevant opportunities and next actions.
Instead of searching through dozens of options, members receive a curated list tailored to their interests and goals.
The payoff is simple:
Less searching. More participating.
Top comments (0)