Skip navigation
We turned Jev into a general browser skill for agents: jev-browser.
0:00 / 0:22

We turned Jev into a general browser skill for agents: jev-browser.

AI Builder Club

@aibuilderclub_6.6K followers

Visit on X
404 likesDownloadOriginal post

34,077 views

We turned Jev into a general browser skill for agents: jev-browser. Give it a website and a task. The browser opens automatically, and Jev decides every click based on what's on the screen. Here's a demo:

27 Comments

Comments from the original post on X (Twitter)

  • Jon Kraayenbrink's profile picture

    @kraayenJon

    did you open source this project? would love to feature it in

    2 likes

  • AI Builder Club's profile picture

    @aibuilderclub_

    Thanks! Once we've polished it up a bit more, we'll open source it.

    4 likes

  • AI Mastery Guide's profile picture

    @aiseomastery

    Jev picking every click is wild.

    1 like

  • AI Builder Club's profile picture

    @aibuilderclub_

    been trying it the last couple days. automating some stuff with it and it’s actually so useful

  • Alessandro's profile picture

    @aleisonx

    I was definitely looking for this, where can I find it?

    1 like

  • AI Builder Club's profile picture

    @aibuilderclub_

    We'll be sharing it inside our community. If you're interested, feel free to join us.

  • Alessandro's profile picture

    @aleisonx

    Sure! Will it be an open repo or will be behind paywall?

  • Asaf Mazuz's profile picture

    @MazuzAsaf

    Do you have a public repo for this? Or is this a closed solution that you built?

    1 like

  • AI Builder Club's profile picture

    @aibuilderclub_

    We've already shared it in our community. Once it's a bit more polished, we'll consider open-sourcing it too.

    1 like

  • Tobi's profile picture

    @tobiadonadon_

    seeing the page can choose a click. reliable work still needs a second layer: permission boundaries and a check that the intended result actually happened.seeing the page can choose a click. reliable work still needs a second layer: permission boundaries and a check that the intended result actually happened.

  • MASA's profile picture

    @themahis

    How does it handle unexpected popups or captchas?

  • Artemi Vaarakallio's profile picture

    @aaapinen

    the useful boundary is screen state to next action. that makes the same skill portable across sites without hardcoding each flow

  • Fajar M Reza's profile picture

    @FReza1984

    A dedicated browser decision layer could make agent automation feel genuinely autonomous.

  • Aby Varghese's profile picture

    @abyvarghese2000

    Where can I get them?

  • AI Builder Club's profile picture

    @aibuilderclub_

    I’ve shared it in our community for now. Planning to open source it later, so keep an eye out.

  • Lennox's profile picture

    @xchatgcp

    把浏览器操作变成可评估的决策层,关键是失败回放和可观测性,速度只是结果之一。

  • AI Builder Club's profile picture

    @aibuilderclub_

    I think a lot of automation tasks that involve decision-making could be handled by Jev. It's a very general-purpose decision layer.

  • Nines's profile picture

    @noninesdev

    The useful leap here is making the browser handle the setup and the clicks, not just generate instructions. Reliability is what will make this kind of agent genuinely useful.

  • AI Builder Club's profile picture

    @aibuilderclub_

    The cost and speed are probably the biggest wins for me.

  • Asklv's profile picture

    @Asklv123123123

    The important bit is re-reading the page after every click. Otherwise Jev is choosing from a screen that no longer exists.