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.
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.
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!
Developer from India. I build open source tools and AI agents. Made OpenFile, 360+ free file tools that run in your browser. github.com/aniruddhaadak80
Location
India
Work
Developer building open source tools and AI agents
CEO & Technical Director at GTSol360. Building AI chatbots,
web and mobile apps, automation, and digital marketing for
global businesses. Karachi, Pakistan.
I'm an Android developer with a growing focus on Reverse Engineering. I love building real-world products, contributing to open source, and learning how large-scale systems work under the hood.
This is awesome. Open-weight models are changing the game, and Hacktoberfest is the perfect excuse to hack on them. Good luck to everyone competing in Week 1! 🚀
I am Samridhi Tripathi , a 3rd year computer science student passionate about exploring emerging AI technologies . I have interest in web devlopment and machiene learning
any tips for keeping ci fast when the repo pulls in large model weights? i usually split the model into a separate artifact and only download it in a post‑install step
Software engineer in the making, collecting little ideas and turning them into things that work. 🌷 I like pretty interfaces, curious problems, creative coding, and building projects that feel a littl
Hey developers wanna give me some advice? I wondered how I could get people to try out my project without telling them they were essentially AI-training machines -like CAPTCHAs- and this is what came of it xd It turned out to be a fun experience in the end, but take a look and tell me: do you think it’s a bit too much or not?
Developer from India. I build open source tools and AI agents. Made OpenFile, 360+ free file tools that run in your browser. github.com/aniruddhaadak80
Location
India
Work
Developer building open source tools and AI agents
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.
I built a page that listens to your birth story and draws your real constellation with open-weight AI ears, verified astronomy brains, and an ending that sends you outside.
I’m reaching out regarding the Virtual Sticker Launch Weekend DEV Challenge. I participated as part of a team in the submission "SUNDEBT: I Made My Phone Charge Me Rent in Sunlight".
The challenge rules state that team submissions are supported and that collaborators’ DEV handles should be listed so the entire team can receive the completion badge. However, I have not yet received my virtual sticker for this challenge.
I wanted to check whether there is any additional action required from my side, or if there is a different process for team members to be awarded the virtual sticker.
Hi DEV team! My Week 1 Hacktoberfest Open-Source AI Challenge submission, IRL Quest, was published on October 8 and edited on October 11 to match the submission template. The required #devchallenge and #hf26challenge tags are visible on the public post, but the article still doesn't appear in View Entries.
Could you please verify whether my submission was registered correctly and let me know if any further action is needed?
what's the plan for handling the compute cost of training models on a week‑long hackathon given typical gpu time and data ingestion bottlenecks? also, how will you ensure reproducibility when participants ship ad‑hoc scripts without a ci pipeline
Hi, my name is Harald and I'm a passionate programmer interested in web development. I'm currently located in Austria working as a Senior Software Developer and Technical Leader for Anexia.
A Developer focused on building AI-powered applications, backend systems, and practical digital products. I enjoy solving real-world problems, creating useful projects, and sharing what I learn.
Since the submission deadline is 11 October 2026 at 11:59 PM PDT (which corresponds to 12 October 2026 at 11:59 AM PKT), could you please confirm if we can submit by our local Pakistan time? Thanks
any thoughts on using supabase edge functions for hosting lightweight transformers? i've hit some jitter streaming model outputs over websockets and wonder if others have a smoother setup
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
Excited!
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.
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.
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!
Hope u all like this
Sanity Challenge Path One Submission
I built an adjudication desk for data that contradicts itself (Both Sides)
Interesting
Excited
Less goo ! New Challenge accepted :)
😁
interesting🤑
Excited !!
This is awesome. Open-weight models are changing the game, and Hacktoberfest is the perfect excuse to hack on them. Good luck to everyone competing in Week 1! 🚀
Here we go again, My Hacktoberfest Open-Source AI Challenge: Week 1
click here to check it out
Back to work
Oh great, another work week...😍
this is great am getting in right now
interesting very excited to build one
Excited!!
Let go, giving it all it takes
Nice
Excited for this
super excited to work on something new
any tips for keeping ci fast when the repo pulls in large model weights? i usually split the model into a separate artifact and only download it in a post‑install step
💖
Now let all go outside and touch grass
dev.to/raphelevator/touch-grass-no...
Hey developers wanna give me some advice? I wondered how I could get people to try out my project without telling them they were essentially AI-training machines -like CAPTCHAs- and this is what came of it xd It turned out to be a fun experience in the end, but take a look and tell me: do you think it’s a bit too much or not?
dev.to/iclaldogan/the-unheard-a-ga...
I built Chrome Extension for Dev.to family. You will read/find more interesting articles than you can imagine ❤️❤️❤️
This post below is not part of my submission, but highly inspired by Hacktoberfest and use of local AI.
I wanted to read more of DEV.to. So I built it into my New Tab
Hacktoberfest: Maintainer Spotlight
I built khata for my sister: the household ledger that reads your payment messages
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
good stuff
youtu.be/o-0b8PfO5kI
dev.to/morningstarxcdcode/i-asked-...
baby-cat-morningstarxcdcodes-proje...
I built a page that listens to your birth story and draws your real constellation with open-weight AI ears, verified astronomy brains, and an ending that sends you outside.
Hi DEV Team & @heyitsjem ,
I’m reaching out regarding the Virtual Sticker Launch Weekend DEV Challenge. I participated as part of a team in the submission "SUNDEBT: I Made My Phone Charge Me Rent in Sunlight".
Project Details:
GitHub: github.com/justsamridhi/SUNDEBT
DEV Submission: dev.to/justsamridhi/sundebt-i-made...
The project was submitted as a team entry, and I am listed as a contributor in the submission:
Name: Aditya Modani
DEV Profile: @modapk06
The challenge rules state that team submissions are supported and that collaborators’ DEV handles should be listed so the entire team can receive the completion badge. However, I have not yet received my virtual sticker for this challenge.
I wanted to check whether there is any additional action required from my side, or if there is a different process for team members to be awarded the virtual sticker.
Thank you for your help!
Hi DEV team! My Week 1 Hacktoberfest Open-Source AI Challenge submission, IRL Quest, was published on October 8 and edited on October 11 to match the submission template. The required #devchallenge and #hf26challenge tags are visible on the public post, but the article still doesn't appear in View Entries.
Could you please verify whether my submission was registered correctly and let me know if any further action is needed?
Post: dev.to/ani0811/irl-quest-ai-that-g...
Thank you!
FYI:
what's the plan for handling the compute cost of training models on a week‑long hackathon given typical gpu time and data ingestion bottlenecks? also, how will you ensure reproducibility when participants ship ad‑hoc scripts without a ci pipeline
how to submit
just create post and submit it right
Yes! Make sure to use the official submissions template.
Is there a reason why my submission was not accepted for the
Week 1 DEV Challenge? dev.to/nezhar/lookabout-a-photo-wa...Hey @nezhar, your submission looks valid to me. We haven't announced winners just yet. Is there a specific concern you have?
Since the submission deadline is 11 October 2026 at 11:59 PM PDT (which corresponds to 12 October 2026 at 11:59 AM PKT), could you please confirm if we can submit by our local Pakistan time? Thanks
Yes, everyone submits according to their corresponding local time!
What if my project idea is unknowingly copied by other participant
Whose post will be counted as valid?
Hello ALL!
I hope you all like this
dev.to/blessloaded/afk-engine-what...
Hi
💯
any thoughts on using supabase edge functions for hosting lightweight transformers? i've hit some jitter streaming model outputs over websockets and wonder if others have a smoother setup
intresting
Hi
okay I can🥰
Hi, I'm a software engineer. I write about build systems, CI, and bugs that show up after a release. Glad to be here.
Hi All Developers
dev.to/abhinav_dwivedi_0fdba8ac6/b...
see my work on this
hello