Jem

for The DEV Team

Posted on Oct 5 AI-assisted

Join the Hacktoberfest Open-Source AI Challenge: Touch Grass! $2,450 in Prizes Across 17 Winners.

#devchallenge #hf26challenge #hacktoberfest #softwaredevelopment

Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass Submission 🌿

Week 1 of our five Hacktoberfest DEV Challenges starts today! Running through October 11, the Hacktoberfest Open-Source AI Challenge: Week 1 gives you a full week to build.

**This year's Hacktoberfest is all about building brand-new projects with open-source AI and open-weight models. Here's everything you need to know about Hacktoberfest 2026.

Missed the Hacktoberfest Weekend Challenge? No problem. Every challenge is a fresh start, so you're competing on the same footing as everyone else.

This week, we'll select one overall winner and a winner in each of our 16 partner categories. See all five challenges and every partner category on the HF26 DEV Challenge Hub.

Let's get to it!

This week's theme: Touch Grass

Build something with open-weight models or open-source AI that gets people off the screen and into the world.

That can mean running an open-weight model, building on an open-source agent harness or framework, running inference locally, or all three. Whatever you pick, the open pieces should be what makes your project work.

Hiking, gardening, birding, run clubs, fall foliage: if it gets someone outside, it counts. The best builds here should make the screen the shortest part of the experience. A few ideas to get you going:

A bird call identifier that works on the trail with no signal
A garden planner that tells you what to plant this week based on your local frost dates
A run club route builder that finds the best fall foliage near you

In your post, tell us why open innovation matters for what you built. Does it run on a phone in the backcountry with no internet? Keep someone's location data off a server they don't control? Let you fine-tune, swap models, or change how your agent behaves? Cost nothing to run? Tell us where your open-based approach worked better than a closed one.

Bonus points if you take it outside, use it, and tell us how it went.

Touch Grass Submission Template

Prize Categories

Alongside our overall winner, we have 16 prize categories for projects that use a specific partner's technology. You don't need to use any of these to win the overall prize, but if you've been curious about any of this tech, this is a great excuse to give one a try. Full descriptions are on the hub.

Featured categories:

Partner categories:

Pro Tip: Partner category winners come from a smaller pool of submissions, so your odds are meaningfully higher.

Note: One project can enter every category it genuinely uses, but you can only win once per challenge, and we'll aim to celebrate as many different builders as possible across the month.

Free credits: several partners are giving participants credits and promo codes, including Tinker, Render, Backboard, and ElevenLabs. Claim yours at hacktoberfest.com/my.

A huge thank you to our partners for making these prizes possible!

Judging Criteria

This is DEV, so your write-up matters most.

Writing Quality (weighted most heavily): Is the post clear and engaging? Does it explain what you built, who it's for, and why open innovation matters?
Relevance to the Prompt and Theme: Is open-source AI or open-weight models at the core of the project? Does it get people off the screen and into the world?
Creativity: Is it an original idea, or a fresh take on a familiar problem?
Technical Execution: Does it work, and is it well built?
Use of Partner Technology (optional): If you're entering a partner category, does the project use that technology in a meaningful way?

Show your work. We'd love to see how you built it. Save your agent session with DevRelay and embed it in your post, or link to it. It's optional, but it helps the judges understand your process.

Prizes

Overall winner (1): $250 USD, a DEV++ membership, and an exclusive DEV badge
Featured category winners (6): $200 USD and an exclusive DEV badge each
Partner category winners (10): $100 USD and an exclusive DEV badge each

All participants with a valid submission will receive a completion badge.

How To Participate

Publish a post on DEV using the submission template below. Tell us what you built and how it gets people outside, show us a demo, and explain why open innovation matters for what you built.

Touch Grass Submission Template

Please review our judging criteria, rules, guidelines, and FAQ page before submitting so you understand our participation guidelines and official contest rules, such as eligibility requirements.

Need Help?

New to Hacktoberfest this year? Start with Everything You Need To Know About Hacktoberfest 2026.
Come hang out and ask questions in the MLH Discord.
The challenge page has resources from our partners to help you get started.

Important Dates

October 5: Hacktoberfest Open-Source AI Challenge: Week 1 begins!
October 11: Submissions due at 11:59 PM PDT
Week of October 12: Winners announced

Week 2 launches Monday, October 12 with a brand-new theme. Follow #hf26challenge so you don't miss the reveal.

Questions about the challenge? Drop them in the comments below.

Happy Hacktoberfest, and good luck!

Top comments (39)

Ariba Sayed • Oct 5

Excited!

adriens • Oct 5

First benefit of this Hackathon, I used Kaggle and its free GPUs in a brand new way, will make me more productive in my next projects

ANIRUDDHA ADAK • Oct 6

Hacktoberfest: Maintainer Spotlight

ANIRUDDHA ADAK

Oct 3

I built khata for my sister: the household ledger that reads your payment messages

#hf26challenge #opensource #nextjs #hacktoberfest

11 min read

Oleksandr • Oct 6

Focusing this year's Hacktoberfest entirely on open-weight models and open-source AI is a massive win for the dev ecosystem. Building apps that interface with the physical world while keeping the data layer local and private is exactly where tech needs to go. Sticking a LLM framework into outdoor logistics or hardware sensors sounds like an elite challenge. Let's get to it!

shieldx • Oct 6

The focus on AI-related open-source contributions for this Hacktoberfest challenge is a smart move, especially since the barrier to entry for high-quality AI tooling has shifted so much recently. One thing to watch out for when contributing to AI repos is the documentation. A lot of these projects have incredible core logic but struggle with explaining how to actually interface with their models or handle specific edge cases in the API responses. If you're looking to stand out, focusing on improving the integration guides or adding comprehensive unit tests for model outputs can often be more valuable to maintainers than just adding new features.

Oleksandr • Oct 7

Heavy agree on this, shieldx. Developer Experience (DX) in the current AI open-source ecosystem is honestly pretty rough. A lot of maintainers are brilliant researchers but they ship projects without clear integration vectors. Writing solid docs or fixing flaky API error-handling is a massive force multiplier for the project. Plus, it’s a much faster way to get your PR merged than trying to refactor their core logic.

ANIRUDDHA ADAK • Oct 6

Hope u all like this

Sanity Challenge Path One Submission

ANIRUDDHA ADAK

Oct 3

I built an adjudication desk for data that contradicts itself (Both Sides)

#sanitychallenge #sanity #mcp #nextjs

9 min read

Elev 💥 • Oct 7

Every "go outside" app I've tried has the same problem. It's an app, so it wants you to look at it.

So for the @thepracticaldev Hacktoberfest Open-Source AI Challenge, I built the opposite.

Touch Grass, Not Glass is a camera that only works outside, and it won't show you anything until you get home.

Here's how it works:

At home, you load the film. You tell it where you're going, and Gemma 3, an open model running on my own laptop through @ollama, writes you six small things to find.

Outside, the screen goes almost black. One mission at a time, read out loud, and a single button: "I found it". No feed, no map, no preview. You take the photo and the phone goes back in your pocket.

Back home, you develop the roll. Gemma looks at each photo, writes down what it actually sees, then decides if you found it. Every walk turns into a page in a little field journal.

The app keeps one number: how long your screen was off.

The funny part is the slowness. My laptop has no graphics card, so developing one photo takes about two minutes. At first that felt like a problem. Then I realised it was the whole idea. Film cameras made you wait too. You shoot now and see later, and the screen gets to stay dark.

It also gets things wrong, and I left that in. It once called a slug a snail. I made a short voxel film about that moment, with a robot laptop, a kid called Sam and a very sad trombone.

Why open AI matters here:
It works where there's no signal.
Your photos never leave your own devices.
It costs nothing to run.
I can swap the model or fine tune it whenever I want.

Try it: touch-grass-not-glass.vercel.app
Code: github.com/angelraph/touch-grass-n...

The full story, how I built it and what Gemma got wrong are on DEV:

dev.to/raphelevator/touch-grass-no...

Now go outside. 🌿

@hacktoberfest2024