The easiest way to automate the web.
San Francisco
- Tweets 1,556
- Following 12
- Followers 42,921
- Likes 1,902
Pinned Tweet
Introducing: New Browser Infrastructure. ⚡️
Chromium fork. Firecracker fork. Custom Linux kernel.
> 3x cheaper. $0.02/h.
> Unlimited scaling
> Subsecond cold starts
> Most stealth browser infra
Feel the speed. Now live.
Try it now ↓
50
74
1,200
383,449
GLM 5.2 ⚔️ Opus 4.7 ⚔️ GPT 5.5 ⚔️ Minimax M3
Should you use open-weight models?
We're making a QA benchmark.
Using Browser Use v4, we benchmarked these models
> Send a task from the LLM Arena dataset to each
> Generate the website, score with human evaluation
Which model did the best?
Check it out ↓
19
11
195
20,381
Check out the other tasks here:
showcase.browser-use.tools/?…
1
1,360
Opus 4.7 ⚔️ GLM 5.2
We're benchmarking models on frontend design.
We run each model on Browser Use v4
> One prompt from the public LLM Arena dataset
> Generate websites and score them
Who won?
Check it out ↓
7
4
154
28,778
Browser Use retweeted
Our new cloud agent (live tomorrow) can make posters!
Its so much nicer to see information in a styled page than plaintext. It can actually do a lot more than just posters, but more on that later...
Try it tomorrow!
3
4
28
18,298
Browser Harness in the cloud is live (beta).
Break it so @larsencc and @Alezander907 can fix it 🫶
Hear me out... Browser Harness but in the Cloud (beta).
Built on:
> Browsercode (thanks @Alezander907)
> AWS AgentCore
> Custom Control Plane
Try it in the UI, or comment API V4 for early API access ↓
5
3
58
7,699
We're giving away browsers for free via our free tier!
Send this to your agent to try it out:
browser-use.com/stealth-brow…
1
7
1,845
GLM 5.2 just beat Fable 5 at website design. 🌐
The crazy part: GLM is text-only.
It can build the site, but it can’t inspect the result.
So we paired it with Browser Use v2 multimodal QA subagents.
> Reviews the site and finds bugs
> Judges the aesthetics
> Sends GLM targeted fixes to iterate on
Build + full QA cost less than $0.75.
Try it now ↓
60
172
2,212
268,490
Send this to GLM 5.2 in OpenCode or BrowserCode:
docs.browser-use.com/open-so…
40
5,023
Open-weights models have officially caught up
We tried GLM 5.2 in BrowserCode
> Near Opus-level score
> Cheapest model to date
This task took $0.18
Try it now ↓
GLM 5.2 is a huge improvement for browser agents, offering near opus level score, beating GPT 5.5
Minimax M3 is a sonnet level score at just $0.30 input, my new best value model (cheaper than deepseek v4 pro)
Kimi k2.7 is a +9% improvement from k2.6 but is outclassed by M3
17
45
627
75,409
Try GLM 5.2 in BrowserCode, our browser agent harness
github.com/browser-use/brows…
2
1
28
2,988
Make full slideshows in seconds using BrowserCode! 🧑🎓
Our v4 agent creates photos, slideshows, and videos!
> Analyzes the content to gain context
> Creates the media file wrt the content
> Users can download from the agent's session
All it took was one prompt!
Try it now ↓
8
2
49
4,935
Create a slideshow using v4 here:
cloud.browser-use.com/v4?utm…
1
4
1,145
This is how easy it is to deploy B, your browser agent!
Introducing B, a browser agent template!
Built on Eve by @vercel. Give any agent a real Browser Use Cloud browser. Watch it browse in real time using browser-harness.
github.com/browser-use/brows…
3
1
56
5,919
View B's cloud browser sessions here!
cloud.browser-use.com/browse…
1
1,073
Introducing B, a browser agent template!
Built on Eve by @vercel. Give any agent a real Browser Use Cloud browser. Watch it browse in real time using browser-harness.
github.com/browser-use/brows…
8
10
97
31,956
View your cloud browser and more here:
cloud.browser-use.com/browse…
5
1,820