Skip navigation
Combined Jev with Playwright-controlled Chrome to build jev-browser, a general browser automation…
0:00 / 0:31

Combined Jev with Playwright-controlled Chrome to build jev-browser, a general browser automation…

Kai

@hqmank15K followers

Visit on X
415 likesDownloadOriginal post

48,403 views

Combined Jev with Playwright-controlled Chrome to build jev-browser, a general browser automation skill. Works across agents. Two demos in Antigravity CLI and Codex: finding related articles, then job openings on a site. Both ran fast. This could handle many more browser tasks.

41 Comments

Comments from the original post on X (Twitter)

  • Pavan GK's profile picture

    @ItsPavanGK

    I built this as a non-coder. Imagine what the nerds do.

    5 likes

  • Kai's profile picture

    @hqmank

    This looks pretty cool.

    1 like

  • Pavan GK's profile picture

    @ItsPavanGK

    Thanks.

  • catman's profile picture

    @catmanyau

    Jev supplies the agent's reasoning while Playwright supplies reliable browser control, so the same skill can transfer across agents instead of being locked to one tool.

    4 likes

  • Kai's profile picture

    @hqmank

    Exactly. It can handle pretty general browser tasks this way.

    2 likes

  • catman's profile picture

    @catmanyau

    when you say “general browser tasks,” do you mean multi-step flows like research + form filling, or mostly single-site actions?

  • Kostya | AI's profile picture

    @KostyaAI

    Running systematic latency and resource‑usage benchmarks across varied page loads will reveal how jev-browser scales, while security checks on script injection and cookie handling add confidence for broader deployment.

    2 likes

  • Kai's profile picture

    @hqmank

    It’s still more of a personal tool for now. There are definitely a lot more details to think through if you want to use it at scale.

    1 like

  • Fatya's profile picture

    @Narmifatya

    Combining browser control with agents allows them to find articles and job openings. This demonstrates how agents can be equipped with general skills to execute diverse online tasks.

    1 like

  • decipherx's profile picture

    @stacktrace01

    2fa is exactly where this needs a human handoff state, not a stronger model. pause at the code field, preserve the page and resume with a fresh screenshot after the user enters it.

    1 like

  • GS.ai's profile picture

    @gauravsainicom

    Why not run the model locally as well Meet Kevin 🤝

    1 like

  • AI Mastery Guide's profile picture

    @aiseomastery

    Job hunting with this sounds useful.

  • GitTested's profile picture

    @GitTested

    How does it handle interactive elements that are not obvious by inspecting the DOM itself? Like a div that triggers some JS on click.

  • Vlad Terin's profile picture

    @VladTerin

    nice, the cross-agent angle is cool. i went the existing Codex browser-tools route with Jev choosing the next click. how are you verifying each hop in yours?

  • SHRED's profile picture

    @shredbuilds

    @hqmank related articles is the warmup. job openings is why Playwright's holding Chrome.

  • Towhid Khan's profile picture

    @yourtowhid

    What does the skill hand Jev on each step? TypeSafe's own writeup says it takes structured program state as text rather than images, so I am curious whether you feed it the accessibility tree, a DOM digest, or something you rolled yourself.

  • Kai's profile picture

    @hqmank

    First, it parses the DOM to get all the actionable elements on the page. Jev then picks the most likely element + action, like clicking a link or typing into an input. It executes that action and repeats the loop.

  • Towhid Khan's profile picture

    @yourtowhid

    A real page's actionable set blows past Jev's 32k state-plus-longest-question budget fast. Do you rank the candidates down before they go in, or does the whole list ride in the Choice options?

  • Nitiksh · NTXM's profile picture

    @Nitikshofficial

    Love the Jev + real Chrome angle. Once you have a decision layer, the boring part is still the browser control plane: keep a real session, see what it sees, and give the agent deterministic actions. I went the "desktop Chromium with a localhost REST API" route for that. page_map / click / type / wait / screenshot on 127.0.0.1:9090, so any agent runtime can drive it without bolting on a full Playwright stack every time. Shipped as NTXM Browser (Windows, CEF). Early, but the loop feels solid for demos like related articles / job pages.

  • ravioli's profile picture

    @PeopleLover5

    does this require the actual jev model?