Vibium

Dev tools

browser automation

SHOW HN2025

Legend

Vibium

Browser automation for AI and humans, by Selenium's creator

github.com

#browser automation#webdriver bidi#selenium alternative#mcp server#ai agents

443points
124comments
#95of 3,837 in 2025
Top 3%of 2025 by points

How HN took it

LovedMost comments that take a side are positive

13 positive, 44 neutral or asking, 0 mixed, 2 critical, out of 59 comments about the project. Thread score +0.19.

Execution: 3 for, 2 againstIdea: 3 for, 0 against

The thread, comment by comment

Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.

positive neutral or mixed critical about another commenter or something else the maker

What HN said

What people liked

  • Thanks for Selenium and its impact on careers

    From 4 comments
    • Hey man, just wanted to say thanks for Selenium - it was a game changer and had a big impact on my professional life. I’m interested in checking out Vibium - I’ve been a…
      rukuu001 on HN
    • I recently conducted a little research project involving YouTube comments, where selenium made it possible. Quite cool to see the legend here, still active. Thanks, from a very…
      eth0up on HN
    • Hey! You really helped my career. We chatted a lot maybe 13-15 years ago and really helped atlassian scale their selenium tests at the time. So glad to see you are still in this…
      jaredwy on HN
    • The good old days of browser automation! Thanks a lot for Selenium and all the best for Vibium :)
      saikatsg on HN
  • Playwright-style usability goal and open standards approach

    From 1 comment
    • As someone who's made a good living primarily in UI automation for over a decade, thank you. It's been an interesting journey.I do think Playwright is the defacto standard now,…
      999900000999 on HN

Objections

  • Lacks network request monitoring and JS injection in v1

    From 2 comments
    • Does it allow you to inject js, modify the DOM, and most crucially monitor/modify network requests? I do those things in probably 95-99% of the time I reach for playwright mcp in…
      dmd on HN
    • > inject js, modify the DOM, and most crucially monitor/modify network requests not yet. definitely on the roadmap, though. goal is to embrace what playwright has done well, then…
      hugs on HN
  • Not yet production-ready, only v1

    From 1 comment
    • it's just v1. good for experimenting, not for production (yet!) and yes it's perhaps impolite and silently taboo for me to say it out loud, but "not being controlled by…
      hugs on HN
  • Claude Desktop config fails to install

    From 1 comment
    • How do you install it into Claude Desktop? I tried the following, but it fails. ``` "vibium": { "command": "npx", "args": [ "-y", "@vibium/mcp@latest" ] } ```
      starik36 on HN
  • Python and Java support not yet available

    From 2 comments

Requests

  • Support for codex and other agents

    From 1 comment
  • Local model support such as llama.cpp

    From 1 comment
    • Any plans to support local models through llama.cpp or similar?
      pryelluw on HN
  • URL allowlisting for safer agent use

    From 1 comment
    • I'd love to be able to lock down the browser to only allow certain URLs (e.g. localhost) so I can give Claude (and other tools) carte blanche to use browser automation (rather…
      moss_dog on HN
  • Agent skills support

    From 1 comment
    • I wasn’t able to gather the future state plans beyond what’s noted in the V2 plans: https://github.com/VibiumDev/vibium/blob/main/V2-ROADMAP.md What’s next 5 years look like…
      rancar2 on HN

Questions

  • How does it compare to Playwright

    From 3 comments
    • My number one question would be how it compares to Playwright -- differences in design goals, capabilities, advantages and disadvantages.
      anamexis on HN
    • As someone who's made a good living primarily in UI automation for over a decade, thank you. It's been an interesting journey.I do think Playwright is the defacto standard now,…
      999900000999 on HN
    • What is the benefit of using this instead of playwright?
      ripped_britches on HN
  • How does it handle context bloat

    From 1 comment
    • How does it handle context bloat between the browser and the llm? Any plans of exposing more of the browser? For instance playwright is able to store tracing files the agent may…
      hcoura on HN
  • Does it handle login sessions and cookies

    From 1 comment
    • And this handles login sessions, cookies, etc.? So much of the modern web is now hidden behind login sessions.
      didip on HN
  • Prompt injection risk from malicious pages

    From 1 comment
    • Is there any plan about how to deal with indirect prompt injection attacks that could trivially be lurking in malicious web pages, given the agent can navigate to an arbitrary URL?
      gsnedders on HN

Alternatives named

  • Playwright and Playwright MCP

    From 3 comments
    • As someone who's made a good living primarily in UI automation for over a decade, thank you. It's been an interesting journey.I do think Playwright is the defacto standard now,…
      999900000999 on HN
    • Does it allow you to inject js, modify the DOM, and most crucially monitor/modify network requests? I do those things in probably 95-99% of the time I reach for playwright mcp in…
      dmd on HN
    • My number one question would be how it compares to Playwright -- differences in design goals, capabilities, advantages and disadvantages.
      anamexis on HN
  • Selenium

    From 1 comment
    • This is very cool. We were thinking about doing something very similar with Skyvern What was the reason you went down this path instead of extending selenium with AI features?
      suchintan on HN
  • dev-browser skill

    From 1 comment
    • Interesting, I've been using this skill https://github.com/SawyerHood/dev-browser to save on context and get some more speed. Will try this out!
      michelb on HN
  • Stagehand

    From 1 comment

Category, keywords, summaries and labels on this page were made by AI (Thread Reader v2) and not checked by hand. Each point links to the comments it came from.

Add a badge to your READMEShown on HackerShow
[![Shown on HackerShow](https://hackershow.org/badge.svg)](https://hackershow.org/show/46377597)