Browser Use (@browser_use) header
Browser Use (@browser_use) profile picture

Agents that use the Browser | 200k⭐️

San Francisco
Joined November 2024
Photo by Browser Use (@browser_use)Photo by Browser Use (@browser_use)Photo by Browser Use (@browser_use)Photo by Browser Use (@browser_use)Photo by Browser Use (@browser_use)Photo by Browser Use (@browser_use)Photo by Browser Use (@browser_use)Photo by Browser Use (@browser_use)Photo by Browser Use (@browser_use)Photo by Browser Use (@browser_use)
Challenge?
Browser Use cloud browsers can bypass anything. I will give you $100 amazon gift card if you find a website that blocks us 100% of time. comments ↓
3
19
3,605
Browser Use is all you need
12
46
5,592
The entire Pareto Frontier is now dominated by Ember
Ran Muse Ember on hardest long horizon browser benchmark 👀 It's EXTREMELY cheap, pareto frontier. Tasks with 100s of browser steps cost CENTS, not USD > 63.9/100, same as GPT-6 Luna medium > 3 cents a task, 2.4x cheaper > best score under 5 cents congrats @alexandr_wang, cheap models that can actually drive a browser are huge
4
6
2
104
7,811
Try our cloud, we bypass everything
Replying to @browser_use
@browser_use has solved captchas. their stealth browser is so good that you essentially never get captcha blocked anymore. there are probably some very very lucrative ideas that stem from this.
6
5
255
14,687
Introducing: Browser Use 1.0.0: CDP is all you need 👀 We deleted 90% of the old library. Predefined state and action space make it worse. Now the agent just writes Python REPL on raw CDP. Simplicity wins. > same models, up to 50% better > 2-5x cheaper > 2-3x faster > SOTA web agent From now on we ship fast. Please pin with ==
48
86
19
1,165
191,464
Ran Muse Ember on hardest long horizon browser benchmark 👀 It's EXTREMELY cheap, pareto frontier. Tasks with 100s of browser steps cost CENTS, not USD > 63.9/100, same as GPT-6 Luna medium > 3 cents a task, 2.4x cheaper > best score under 5 cents congrats @alexandr_wang, cheap models that can actually drive a browser are huge
12
16
7
203
27,929
little browser agent hack: stop sending screenshots to find buttons. ask Chrome for the accessibility tree: cdp("Accessibility.getFullAXTree") > every element with role, name and node id > filter to links, buttons, inputs > DOM.getBoxModel -> click the center on Hacker News: 1,764 nodes -> 227 clickable, zero vision tokens Browser Harness agents work this way: github.com/browser-use/brows…
24
11
258
12,699
BU Ultrafast is absolutely goated for phishing detection. For less than $0.01 you can detect very robustly whether website is scam or not. browser-use.com/ultrafast
3
3
1
39
3,930
If you want 10k concurrent browsers without spending X00k on a browser provider dm (we are PAYG)
2
1
32
4,886
Your agent shouldn't need a pile of subscriptions to get work done. With @composio Instant it can run Browser Use straight from its Composio wallet. We gave them 6k in credits so that you can just try it. Also works with our Ultrafast model. Pay per call, no keys, no signup.composio.dev/instant
9
6
3
63
7,109
Scalable infra wins
We don't care about concurrency, our infra is scalable af. If you want to run thousands of parallel browsers you can do that on PAYG plan, no commitment needed, just dm me. The more concurrency you have the more money we make. (other browser providers charge you for concurrency btw)
2
16
3,382
Folk personal agent is now SOTA at browser use 💯 @textfolk switched their browser harness to Browser Use Pi > 70% fewer tokens > 22% faster > follow-ups keep their browser state Check it out it's awesome folk.com @arlanr 🤝
16
5
2
116
24,728
Released: BU Ultrafast is live for everyone⚡ Fastest and cheapest web agent on the planet. > tasks in under 3s > median task takes 14.4s > $0.126 total for 25 tasks in the video Real time, not sped up. Try it on our cloud today 🔥
19
15
5
256
91,786
Tell your instinct, grok, or muse to install browser-harness to make their browser tool 2x faster.
Browser Use CLI is BY FAR the most effficient browser harness for agents.
94
28
1
808
76,788
Well now you know it's just me (gregor) and my agents running this account
0. browser use - 5 employees
19
2,550
Introducing: Odysseys2 - hardest long horizon benchmark for web agents based on real user tasks 🏗️ We collaborated with @JangLawrenceK @rsalakhu from Carnegie Mellon University > SOTA agent fully completes only 47/100 > 5 agents complete none > 8-12 real rubrics per task, 60 min on the live web Web agents are becoming better than humans at knowledge work. odysseysbench.com/v2
16
9
11
145
17,500
Who wins depends on how long you wait > 15 min: GPT-5.6 Luna 37, Opus 5.5 18 > 36 min: Opus catches up > 60 min: Opus 71, Luna 60 Luna is 18x cheaper ($0.35 vs $6.22 per task)
2
7
1,101
Your agent is only as good as its browser. Ours keeps getting better, nonstop. Getting blocked is now optional. Try it now: cloud.browser-use.com
While others get flagged as bots, @browser_use solves all major anti-bots and CAPTCHAs. SOTA on every public stealth benchmark. Fully headless, with in-house captcha solvers. Now I'm only competing against myself. Blocked somewhere? DMs are open. Blog post soon. 🤓
4
2
33
3,494
BUT the inference is slooow, cmon @Kimi_Moonshot open source it already
Kimi K3.1 Pro is a beast at browser use 🤯 76.8 on the Browser Use Benchmark. Only GPT-6.1 Sol scores higher. It beats Opus 5.5, Grok 4.7 and Sonnet 5.5, and it's cheaper than Opus at ~$2/task. Best Chinese model we've ever tested, by a lot. Next best is DeepSeek V4.1 Flash at 70.6. Moonshot cooked.
1
1
30
2,953