Show HN: Vibium – Browser automation for AI and humans, by Selenium's creator
309 points
by hugs
15 hours ago
| 27 comments
| github.com
| HN
i started the selenium project 21 years ago. vibium is what i'd build if i started over today with ai agents in mind. go binary under the hood (handles browser, bidi, mcp) but devs never see it. just npm install vibium. python/java coming. for claude code: claude mcp add vibium -- npx -y vibium v1 ships today. ama.
rukuu001
13 hours ago
[-]
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 reluctant adopter of Playwright and hopeful for a new approach.

reply
hugs
13 hours ago
[-]
playwright got a lot of things right. one of the big ones was a fast websockets+json way to drive the browser. (vibium is using the w3c standard equivalent - webdriver bidi). but they also raised the bar on usability and developer experience. i hope to get to the level of "click, click, awesome" out-of-the-box experience that playwright did so well.
reply
pkiv
10 hours ago
[-]
If you're already using Playwright, I'd love for you to give Stagehand a try (https://github.com/browserbase/stagehand) - it has compatible-ish API, but built for automation, not testing.
reply
zenmac
16 minutes ago
[-]
Hmmm so it is basically using https://www.director.ai for the AI natural language stuff right?
reply
hugs
9 hours ago
[-]
stagehand is good stuff!
reply
dmd
13 hours ago
[-]
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 claude, and from the "For Agents" part of the README, it seems like all this can do is click/type/screenshot?
reply
hugs
13 hours ago
[-]
> 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 extend what's possible...

reply
dmd
13 hours ago
[-]
Thanks. I would love to understand what people are doing with Playwright that doesn't involve those things. I really can't recall ever using it where that wasn't what I was doing. I use it letting Claude fix things. You can't fix what you can't see! What else are people using it for? Obviously there must be a (very popular!) use case for "just clicking", but I can't seem to imagine it.
reply
Robdel12
12 hours ago
[-]
To me doing network interception in browser driven tests is a smell like that. Unless you’re running vs a full mocked server (like MSW).

I’m a big fan of testing exactly like a user. Users don’t use network intercepts, timeouts, etc. All of my most reliable tests assert on DOM state. If the user doesn’t see it, don’t assert on it.

reply
dmd
12 hours ago
[-]
Almost nothing I do has to do with what users actually see though. It’s all things like “why didn’t the SSO flow work”.
reply
mewpmewp2
8 hours ago
[-]
I guess the issue is that real world does smell terribly. I wish I could just have the perfect World like my side projects always have, but not the case with the commercial ones making money.
reply
VoidWhisperer
12 hours ago
[-]
In my experience, we've used playwright significantly for unit/integration tests combining it with react-testing-library to verify individual components and also whole (mocked, we used something else that I can't seem to remember for E2E tests) flows within that React application
reply
hugs
12 hours ago
[-]
don't underestimate the "just clicking" use case!
reply
therunninglight
12 hours ago
[-]
hugs built an entire career on the "click" case (just making a button work). no wonder, the vibium go binary us called "clicker".
reply
doctorpangloss
11 hours ago
[-]
all i want is monitored network requests, because flutter + amazon appsync apps are so radioactive
reply
hugs
9 hours ago
[-]
good feedback. thank you!
reply
michelb
14 hours ago
[-]
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!
reply
hugs
14 hours ago
[-]
yeah, looking to play more with (and support) skills with vibium soon.
reply
chews
14 hours ago
[-]
big virtual hugs for @hugs... thank you for the Christmas gift of fewer keystrokes :-)
reply
999900000999
14 hours ago
[-]
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, but Selenium was the original browser driver.

Anyway, how does Vibium compare to Playwright ? Playwright's main advantage is it has official support for multiple languages.

reply
hugs
14 hours ago
[-]
> I do think Playwright is the defacto standard now

i'll politely pushback a little. i think it's safe (at this moment in time) to say: playwright wins the first derivative, but selenium wins the "area under the curve". selenium is very entrenched in many parts of the world, especially outside of SF/USA. part of the inbound interest i've been getting for vibium is from those selenium users who want some kind of bridge to the future, but didn't have an obvious path forward beyond "dump selenium, adopt playwright"...

part of my plan with vibium post-v1 is to give that massive (and it truly is massive, i'm not bragging) installed base of selenium users an upgrade path to more agentic coding options.

reply
999900000999
13 hours ago
[-]
Are you solo developing vibium ?

Playwright really simplifies getting setup. It won't work for everyone, but within 30 seconds Playwright will download it's needed browsers along with a test runner.

I also find the documentation is much better/consolidated.

Definitely open to helping you out if I can be of assistance.

reply
hugs
12 hours ago
[-]
"npm install vibium" installs the needed browser on install.

right now, code-wise -- for the code you see in github at the moment -- it's just me and my ai pal, claude. but there's a growing cast of (human!) characters also helping with all the other things we need to do to run a successful project. patches and tokens welcome!

reply
steve_adams_86
13 hours ago
[-]
Selenium is distinctly more popular among scientists in my experience. I've only seen playwright at startups.
reply
zenmac
13 minutes ago
[-]
Isn't Selenium vs Playwright more a Java vs JS/ES/TS thing?
reply
999900000999
6 hours ago
[-]
I've personally implemented Playwright in a large enterprise company. Puppeteer before that.

Generally if you have a lot of legacy selenium scripts it's probably not worth it to switch everything over, but if you're creating a new UI automation framework I've just never seen selenium as a first choice for that.

Don't get me wrong it's still solid technology though.

reply
therunninglight
5 hours ago
[-]
yes, i've noticed some tendency for [agentic] qa services to go the puppeteer and then playwright route (sometimes either or). it's almost too easy to get running with pw. and, hence, enticing for any startup that wants to get off the ground asap and break even. seems vibium may tap into that startup market as it matures.

legacy selenium suites are a strong contender for vibium adoption. i think hugs has been surveying a ton of folks, he may have a better bird's eye view of the potential user base.

as for academic use of selenium, we have boni garcia - maker/popularizer or selenium webdriver manager teaching at a uni in spain. (maybe an isolated example, but he's rather known in the community)

reply
therunninglight
12 hours ago
[-]
same in my experience.
reply
jjmarr
8 hours ago
[-]
Selenium was a part of my degree. I had a course involving it.
reply
moss_dog
14 hours ago
[-]
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 than manually approving each command). Is this something on your radar / roadmap?
reply
ramoz
14 hours ago
[-]
If using Claude Code, a simple hook can govern `browser_navigate` (mcp)

A custom sh script or something for whitelists would take ~5min to setup.

For more robust governance (many policies), you can write Rego using https://github.com/eqtylab/cupcake

https://code.claude.com/docs/en/hooks#mcp-tool-naming

reply
moss_dog
14 hours ago
[-]
Thank you for the links / info! I'm looking forward to digging into this.
reply
hugs
14 hours ago
[-]
fully aware of the "blast radius" risk of using claude to do stuff. i'm doing all my vibium dev in a vm using UTM (and you should, too!). wonder if there are some network rules we can add.

i did post a v2 roadmap on the github repo. might be time to start the draft for v3!

reply
falcor84
14 hours ago
[-]
As I see it, the only real solution is to put it into a container that has a firewall with a short whitelist.
reply
moss_dog
13 hours ago
[-]
I was looking into this earlier -- presumably you'd also need to allowlist Claude itself (whatever endpoints it hits to run inference etc). VM firewall gets a little trickier with Claude's web search tool, too.

The solution I landed on recently was to locally modify the Chrome devtools MCP to launch the browser instance with strict network restrictions. I believe the implementation used `--host-resolver-rules`, blocking all URLs by default with an environment variable to control the allowlist (which, in hindsight, Claude can easily work around if it needs to -- I should probably just hard-code the allowlist).

reply
falcor84
42 minutes ago
[-]
> you'd also need to allowlist Claude itself

This is Anthropic's recommended setup for devcontainers:

https://github.com/anthropics/claude-code/blob/main/.devcont...

You may want to adapt it and particularly to remove the GitHub and VS Code stuff.

reply
rahimnathwani
12 hours ago
[-]
If an agent gets a copy of the screen using browser_screenshot and then wants to click somewhere on that screen, how is it meant to find the right css selector to pass to browser_click?

There's a browser_find method, but that assumes you already know what type of element it is. But I can't always tell what type of element something is just by looking at a screenshot.

What have I missed or misunderstood?

reply
coty
12 hours ago
[-]
For right now, the MCP server doesn’t expose quite enough to navigate on its own.

I’ve added a browser_evaluate tool in my fork—though I haven’t committed or pushed a PR yet. With that, the agent can call JavaScript to get the accessibility tree and then use that to navigate via browser_find.

This and much more will be coming soon. See the V2 roadmap for more insight: https://github.com/VibiumDev/vibium/blob/main/V2-ROADMAP.md

reply
hugs
9 hours ago
[-]
one of the wild things about vibe coding is... i want to add that feature, but i'm slightly more interested in using the prompt/spec you might have used to create it, not the patch itself.
reply
suchintan
15 hours ago
[-]
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?

reply
hugs
14 hours ago
[-]
i partially addressed this in the "why vibium" section of the v1 announcement: https://github.com/VibiumDev/vibium/blob/main/docs/updates/2...

but why a new thing vs extending selenium? it's a little complicated, but neither selenium nor playwright were designed with ai in mind from day 1. with vibium, i'm optimizing for "vibe coding" and ai-driven workflows first.

reply
suchintan
14 hours ago
[-]
This makes sense. I guess I wanted to understand why starting from scratch was better than "fixing" selenium, but perhaps "fixing" selenium isn't an option?
reply
hugs
13 hours ago
[-]
for the entire testing tools industry, in some ways, selenium was the "final boss" to beat. every new tool had to trash selenium in their marketing. eventually those "hit points" added up. "fixing selenium" is as much as of a branding problem as it is a technical problem. "oh, there's a new version of selenium? i heard selenium sucks!" is actually a problem that has to be dealt with. an entire new generation of coders only know "playwright rules, selenium drools".

of course, i have a new host of problems by going all in with "vibium"... i'm making a huge bet that "vibe coding" is a trend, not a fad. (it could still be a fad! we'll see if this post ages well soon enough!)

reply
suchintan
13 hours ago
[-]
That makes a lot of sense. Sometimes it's easier to leave the baggage behind. It's too bad..selenium is a masterpiece. Thanks for sharing it with the world
reply
palidanx
4 hours ago
[-]
Sorry, I kind of have a dumb question here. So we have a bunch of legacy selenium scripts that do end to end user testing, and occasion they break (either because of a network error, or devs committed something that breaks a test).

We were looking at seeing if a model could look at the screenshot of the failure, some of the original website source code, and try to fix the failing test.

My question is with vibium, would it make more sense to port the legacy tests over to vibium, and if a test fail, use its capabilities to try to self-heal?

reply
hugs
3 hours ago
[-]
i apologize, but i'll answer your question with a metaphor.

i want to build an island resort and a bridge from the mainland to get there. do i build the island resort first or the bridge first?

here's my thinking: if the resort is popular and a fun place to be, there will be a huge incentive to build the bridge next. but we might also find out that building the bridge will ultimately be economically impractical and we should just stick to using ferry boats. at least we'll have a cool island resort to go to, though!

so for now, i'm just focusing on building the island resort at the moment. but i really, really want to build that bridge, too, asap.

reply
hcoura
14 hours ago
[-]
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 decide to read to understand some requests / payloads…

Any plans on allowing the agent to run an arbitrary js script?

reply
hugs
14 hours ago
[-]
i definitely have plans to expose more of the browser! at the moment, it's very limited. i'm not sure if anyone has completely nailed the context bloat problem -- it's worth more study and benchmarking. i suspect the long term answer is "don't use mcp". but mcp (warts and all) felt like a table-stakes feature for a v1 release.

also need to clarify: there are two apis exposed right now: the mcp server and a "plain old" js/ts api. the js/api does have the ability to run arbitrary js. theoretically, you could ask an agent to write a vibium script with the js/ts library, and have the ai run that... (which ironically? is also a way to deal with the issue of context bloat)

reply
jaredwy
2 hours ago
[-]
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 space!

reply
anamexis
15 hours ago
[-]
My number one question would be how it compares to Playwright -- differences in design goals, capabilities, advantages and disadvantages.
reply
hugs
15 hours ago
[-]
it's a good questionn! i partially addressed this in the "why vibium" section of the v1 announcement: https://github.com/VibiumDev/vibium/blob/main/docs/updates/2...

to save a click, i'll post it here, too:

-----------

why vibium?

there are dozens of "ai-powered browser" tools now. so why this one?

the selenium ecosystem is massive: millions of tests, thousands of companies, decades of investment. but there's no obvious bridge to the ai future. many have moved to playwright — and for good reason: it's fast, easy to use, has popular features like auto-waiting, integrated video recording, and a ton of other batteries included.

vibium takes the same approach. batteries included. great dx. but built for where the industry is going: ai agents that need to drive browsers.

when i did those interviews in september, the response wasn't just "cool idea." it was relief. the community trusts us to build this bridge because we built the last two: selenium in 2004, appium in 2012.

community and ecosystem are the moat.

reply
anamexis
14 hours ago
[-]
Thanks! I don't think it really answers my question though.

AFAIK Playwright also takes the approach of batteries included, great dx, and has a lot of good integration with AI agents.

Basically, what sets Vibium apart?

reply
therunninglight
12 hours ago
[-]
vibium is hardly 2 days old. the 5-yr plan is grand. quoting hugs "goal is to embrace what playwright has done well, then extend what's possible".
reply
anamexis
5 hours ago
[-]
I appreciate that it's brand new, but I'm still very interested in knowing about what sets it apart, even if that is all just vision at this point. What does "extending what's possible" mean?
reply
hugs
3 hours ago
[-]
i appreciate the persistence in getting an answer. :-)

i was being a little too cute using "embrace" and "extend" in a previous comment (look up "embrace, extend, extinguish"). sorry about that.

the big idea with vibium in v2 and beyond is to bring to test automation something old and boring in robotics: the "sense - think - act" loop. sensors observe the world, a brain makes decisions, and actuators carry them out.

right now most browser tools extend what's possible at the "act" layer. they make it easier for an llm to click, type, and observe the browser.

that's useful, but it mostly enables one-off demos. every run starts from scratch. there's no accumulated understanding of the app, and long workflows are navigated by guessing and retries.

what vibium is trying to extend is not just action, but the loop.

vibium v1 is just the "act" part, which i'm calling clicker. it clicks buttons, types, and navigates the browser.

retina and cortex are coming in v2. retina turns real interaction into durable signal (manual exploration, existing tests, production usage). cortex builds on that signal to create a navigable model of workflows that an llm can plan through, instead of reasoning from raw html each time.

clicker is the execution layer. playwright mcp largely lives here. vibium clicker overlaps in scope, but is designed from the start to feed sensing and planning rather than being the whole system.

so yes, playwright mcp covers part of this. what's missing today is first-class sense and think. that's the gap vibium is exploring, even if v1 only ships the act layer.

tl;dr:

sense -> retina (v2)

think -> cortex (v2)

act -> clicker (v1)

i've spent the past few months talking about applying the "sense - think - act" loop to browser automation, but at some point i realized i needed to "talk less, ship more". :-) i'm looking forward to shipping retina and cortex so we can see whether the full loop is actually a step change beyond what playwright or playwright+mcp can do.

happy to dig deeper if helpful.

reply
rancar2
14 hours ago
[-]
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 given that you are very good at building long-term projects that last and evolve through time? And for a very specific example, what’s the plan for incorporating new standards like Agent Skills as they quickly evolve and launch?

reply
hugs
13 hours ago
[-]
short term: yeah, we should totally add agent skills asap! new year's eve goal?

as far as long term plans go, i like the tim o'reilly quote: "create more value than you capture".

with selenium, we created an entire ecosystem of tools, users, companies, and economic activity. (literally billions of usd -- it's a story frequently ignored by the tech press when looking for "open source success stories".) but i hope to do the same with vibium. there will likely be a hosted "vibium.cloud" hosted service. i also hope there will be lots of them. in a similar way, there weren't many "hosted selenium" services when i started sauce labs. now there's a bunch. browserstack, lambdatest, etc.

it was also not really an accident we did that with selenium. there is a lot of behind-the-scenes consensus building that happens to make things like a w3c webdriver standard happen. (funfact: vibium relies on the new! w3c standard "webdriver bidi" protocol heavily inspired by the chrome devtools protocol used by playwright. (tl;dr: it's just json over websockets.)

i'm betting on industry cooperation, standards, and shared prosperity. that's my 5 year plan!

reply
nivekney
14 hours ago
[-]
Aside from the project itself, I am learning a lot just from reading the commits. Mostly about the process when one knows how they'd do it.

https://github.com/VibiumDev/vibium/commits/main/?after=ffc3...

reply
hugs
8 hours ago
[-]
thanks. if ai-assisted development is the future of software (and i think it is), it was important i put my money where my mouth is and develop it by doing exactly that.
reply
therunninglight
12 hours ago
[-]
likewise, watching it take shape in real time is fascinating
reply
didip
6 hours ago
[-]
And this handles login sessions, cookies, etc.? So much of the modern web is now hidden behind login sessions.
reply
hugs
2 hours ago
[-]
there's generally only 3 ways to make money in browser automation:

1) test automation (my specialty)

2) data scraping / crawling

3) business/robotic process automation (e.g. back-office data entry, processing invoices, etc.)

when it comes to handling login sessions, cookies, etc. test automation is the easiest. (you create disposable test logins and use them in each test. it's mostly a solved problem.)

handling logins is a way gnarlier problem in data scraping and business process automation. i'm focused on test automation in v1. (i'm hoping experts in data scraping and process automation can help me improve vibium in this regard.)

reply
christophilus
15 hours ago
[-]
Nice. I was just thinking of building this very thing. Glad to see I won’t have to. I’ll check it out after the holidays.
reply
hugs
15 hours ago
[-]
what specific things were you looking for?
reply
christophilus
15 hours ago
[-]
My use case is mainly to make it easier to show Claude Code a problem with an SPA as I develop it. Claude’s decent at traditional server-rendered stuff, since it can curl and reason a bit about the responses, but SPAs require something more like your tool here.
reply
xnx
14 hours ago
[-]
You might try Google Antigravity since it is natively designed to test in the browser as it codes.
reply
captainregex
13 hours ago
[-]
entirely possible I’m just really bad at this stuff but I can’t get browser agents to do simple report pulls without running into a captcha or a dropdown menu that breaks its brain. hopefully this is the one!
reply
hugs
13 hours ago
[-]
good security will always be the eternal enemy of easy automation.
reply
therunninglight
12 hours ago
[-]
the realm of bots vs bots
reply
badlogic
14 hours ago
[-]
Neat. Any reason why the MCP server doesn't expose a JavaScript/eval tool? Current models excel at writing JS to drive and inspect the DOM. They aren't great at driving browsers via screenshots.
reply
hugs
14 hours ago
[-]
> why the MCP server doesn't expose a JavaScript/eval tool?

no reason other than my number #1 goal was "ship something". i only started the actual coding on dec 11. it's been a bit of a sprint the last two weeks!

though "image-based" vs "dom-based" testing approaches is a very big topic! (look forward to researching that more in the future.)

v1 announcement: https://github.com/VibiumDev/vibium/blob/main/docs/updates/2...

reply
coty
14 hours ago
[-]
FWIW, if you have Claude Code or the like, you can quickly prompt your way to an eval function in MCP. It already exists in clicker and the client API. You can use it to get the accessibility tree, for example, and use that to find what to fill out and click.
reply
eth0up
3 hours ago
[-]
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 tiny human.

reply
hugs
3 hours ago
[-]
thanks for using it! <heart-emoji/>

i try to say this often, but it never feels like enough: yes, i started the project, but it's a relay race. i ran the first few laps, but the project has been going for 21 years now. there's dozens (hundreds?) of people to thank at this point for the success and impact that the selenium project has achieved.

reply
j2kun
13 hours ago
[-]
Is this something you use to generate static browser tests that no longer use the LLM? Or would you need to use the LLM every time you run the tests?
reply
therunninglight
12 hours ago
[-]
- No LLM Getting Started with Vibium (beginner-friendly): https://github.com/VibiumDev/vibium/blob/main/docs/tutorials...

- MCP option (where tokens will eventually get burned) Getting Started with Vibium MCP: https://github.com/VibiumDev/vibium/blob/main/docs/tutorials...

reply
pryelluw
9 hours ago
[-]
Any plans to support local models through llama.cpp or similar?
reply
hugs
5 hours ago
[-]
100% yes. favorites?
reply
pryelluw
5 hours ago
[-]
I daily drive llama.cpp so that please.
reply
hugs
2 hours ago
[-]
which local models? (e.g. qwen, llama, mistral?)
reply
jstummbillig
10 hours ago
[-]
Cool. Can this currently be used with codex in the same way?
reply
hugs
10 hours ago
[-]
not today. but the plan is to be very "big tent" and support as many options as possible.
reply
jeff4f5da2
13 hours ago
[-]
Since it's in go, wouldn't it be great if it also expose go api?
reply
hugs
13 hours ago
[-]
yes, yes it would!
reply
ripped_britches
14 hours ago
[-]
What is the benefit of using this instead of playwright?
reply
hugs
13 hours ago
[-]
it will be more obvious in v2.

v1 is about getting to a base-line of functionality.

things get interesting in v2: https://github.com/VibiumDev/vibium/blob/main/V2-ROADMAP.md

reply
OutOfHere
12 hours ago
[-]
I will wait for full Python and Go support.
reply
hugs
5 hours ago
[-]
have plans for new year's eve?
reply
therunninglight
11 hours ago
[-]
python client coming soon to PyPi
reply
mannanj
14 hours ago
[-]
Hi this looks really valuable, thanks for developing and sharing. Would you share some use cases and how you or your users use it personally? would love to see some examples and feel the aha "That's how I'd like to use it too!" and it would help me drive and se the problems I have as being solvable by this too rather than seeing a tool/solution looking for a problem. (not implying you're that, but without examples/use cases that's the default way I think)
reply
hugs
14 hours ago
[-]
lots of people have already been posting examples of how they used vibium on linkedin. (code's only been available for a day or two, so we're just getting started!)

we also have a new discord server for the project that we just spun up and will be opening up more widely soon. discord could be a good place to share uses cases and experiments until we set up a more formal website structure).

reply
michaelsbradley
9 hours ago
[-]
Anyone attempting something similar for Qt/QML based apps?
reply
starik36
13 hours ago
[-]
How do you install it into Claude Desktop? I tried the following, but it fails.

    "vibium": {
      "command": "npx",
      "args": [
        "-y",
        "@vibium/mcp@latest"
      ]
    }
reply
therunninglight
12 hours ago
[-]
"vibium": {

"command": "npx",

"args": [

"-y",

"vibium"

]

}

source: https://www.linkedin.com/posts/apzal-bahin_ai-mcp-browseraut...

reply