Vlad Polonskiy

Vlad Polonskiy

Absolute CryptographyAbsolute Cryptography
AI,extella.ai

About

Co-founder at Extella & Chariot Technologies Lab. Built Abscrypt, EasyML, Maria Adviser and more. Now building software that permanently evolves with every problem it solves.

Badges

Tastemaker
Tastemaker
Veteran
Veteran
Gone streaking 10
Gone streaking 10
Gone streaking
Gone streaking
View all badges

Maker History

Forums

The 3 stages of AI usage, where do you actually sit?

I've been building in the AI space for a while now, and I keep seeing the same pattern: most people are using AI the same way they used the early internet. They read, they search, they ask questions. But they're not really building or automating yet.

And that's not a criticism. The internet took years to go from "browse pages" to "infrastructure that runs everything." AI is moving 10xfaster, but the adoption pattern is the same.

Here's what I'm seeing across the community:

  1. Stage one is where most people are right now. They open ChatGPT or Claude, ask a question, copy the answer, close the tab. It's useful, but it's manual.

  2. Stage two is where things get interesting. People are running agents that actually do things. They write code, research topics, process files. But they're still switching between tools, copy-pasting context, managing each agent separately.

  3. Stage three is what I think is actually next, and almost nobody's talking about it yet. One place where your tools, agents, and workflows connect and run together. No stitching between tabs. No manual context switching. The orchestration layer.

Let's turn this thread into the best GitHub reading list on PH.

Let's make this thread useful for everyone.

Drop the GitHub repos you found and actually use. Tools, models, scripts, weird side-projects. Anything you'd recommend to someone curious but short on time.

One link + one sentence on why it's worth knowing about. That's it.

Goal: turn this thread into the most-valuable bookmarked list of GitHub repos every maker should try at least once.
while you're here: you can now install any GitHub repo in one click inside Extella, so anything that lands in this thread is one tap away from being usable. Check it out: https://www.producthunt.com/prod...

The curiosity tax nobody talks about in AI

The number of cool AI tools on GitHub is essentially infinite. The time to try them isn't.
Every interesting repo charges what I'd call a curiosity tax: 30-90 minutes of cloning, installing, fixing dependencies, and hitting a CUDA error before you can even find out whether the tool is worth your attention. The cost isn't in skill. It's in hours spent on setup. And hours are exactly what a lot of us don't have
So most of the interesting tools in AI quietly go untried.
Today we closed that gap. GitHub repo installation is live inside Extella. Browse 630M+ repos, install in one click. What you install becomes a reusable Expert in your workspace.
Try it now: https://www.producthunt.com/prod...
Drop a GitHub link to a tool you think everyone should know about but few people use.

View more