Dev.to is an absolute goldmine. On any given day, thousands of builders share brilliant engineering lessons, launch side projects, break down new AI models, or submit hackathon entries.
The problem is that this massive amount of information is hard to process.
We want to stay updated with the fellow builder community, but nobody has the time to click through fifty long posts just to see what someone built and why it matters.
So, I vibe-coded an internal tool called Dev.to ASSISTANT and decided to open-source it.
See it in action 🎬
Instead of explaining it, here is the tool turning the noise into a clean, structured summary in real-time:
From Infinite Scroll to Instant Value
The goal isn't to skip reading—it's to figure out exactly where to dive deep.
When you pass the assistant a tag (like #weekendchallenge or #ai), it uses a Gemma 4 layer to extract the meat of each post. You instantly get:
The exact "why" and "how" behind the project, stripped of fluff.
What tools, frameworks, or models were used.
Live reaction and comment counts so you can see what's sparking conversation.
A link right back to the original Dev.to post so you can jump in and engage with the author.
Built with the Community, For the Community
Because Dev.to is an open ecosystem that generously provides an official API, I wanted to build this in that exact same spirit.
The backend is built with Python (FastAPI) and the frontend dashboard uses Next.js. I’ve made the entire project completely open-source so any builder can run it locally, tweak the filters, or add new curation features.
If you want to discover great engineering lessons faster, track challenge submissions, or just find amazing people to follow without getting lost in the feed, give it a spin.
Check out the GitHub repository here ⭐️
If this tool helps you find a cool repository or saves you some scroll time, I’d love to hear your thoughts in the comments below!
Top comments (0)