the SDK for browser agents, built by @browserbase join the discord: discord.gg/stagehand
chrome devtools
- Tweets 552
- Following 46
- Followers 5,555
- Likes 1,555
Pinned Tweet
Introducing our Browser Agent Evals.
We benchmark frontier and open models using various harnesses on computer-use tasks.
Our evals are fully open source and reproducible via our Evals CLI.
10
11
35
6,638
Stagehand retweeted
How do you actually build an effective harness with Claude?
We had Thariq (@trq212) from Anthropic at Navigate 2026 to talk about "Unhobbling Claude", the difficulties and processes on how to build agents and harnesses.
6
5
45
8,910
GPT-6 Luna is a step function improvement from it's predecessor scoring 11% higher in accuracy on our browser agent tasks.
GPT-6 Sol scores 2% better in accuracy, but costs 20x more per task than Luna.
GPT-6 Sol and Luna just landed in Astra’s orbit.
Both launch today with API prices 50% lower than GPT-5.6.
Build with Sol. Scale with Luna. To production and beyond.
5
2
15
1,433
Stagehand retweeted
Stripe's new WebMCP endpoint lets your agents make full purchases on the web.
Using @Stagehanddev you can navigate to any Stripe checkout page and use their new WebMCP tools to fill the checkout and fetch order details.
Stagehand can use Stripe's new WebMCP tools in checkout pages.
Run page.tools() to see what WebMCP connectors a page exposes. With Stripe, you can use Stagehand to add items to cart and complete the checkout with native tools.
3
5
42
5,380
Stagehand can use Stripe's new WebMCP tools in checkout pages.
Run page.tools() to see what WebMCP connectors a page exposes. With Stripe, you can use Stagehand to add items to cart and complete the checkout with native tools.
Hi internet! We went ahead and upgraded all @stripe hosted checkout pages for 7.8M businesses—0.45% of the world’s GDP—with WebMCP so agents can more efficiently buy. Our evals show this reduces checkout latency by 39% and token usage by 42%.
Learn more: stripe.dev/blog/how-stripe-i…
3
4
28
6,528
During early testing on our Browser Agent Evals, Opus 5.5 completely crushed it's predecessor Opus 5, but also Fable 5.1 & 5 in accuracy, speed, and, cost.
Compared to Opus 5 in the Claude Code harness it's roughly 5x cheaper per task, and 2x faster.
Introducing Claude Opus 5.5, the first model in our new Claude 5.5 family.
It performs at the level of Claude Fable 5.1 for most tasks, and costs 40% less to run than Opus 5.
8
2
18
1,341
Stagehand retweeted
Jev wasn't meant to build Agents.
Instead, we added it to @Stagehanddev's AI-powered primitives Act, Extract, and Observe.
Rather than a fully autonomous agent, we use Jev as a decision layer: which element to click, field to fill, or text to extract.
18
7
113
8,385
Everyone can build Agentic Commerce using the @link and Browse CLI powered by Stagehand!
it seems like agentic commerce is finally solved with stripe link. and we're excited to partner with stripe to enable all agents to transact online.
your agent can now natively make payments on the web using link cli + browserbase.
one shot prompt: docs.browserbase.com/integra…
3
20
3,001
Stagehand retweeted
we built blazing fast computer/browser use with Jev + @Stagehanddev.
this task cost $0.001 and executed at near instant speed (in a remote browser btw)
the loop: observe the page, send a11y tree as state + actions as questions, Jev decides the next action, then Stagehand executes it.
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI?
I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev
• 20-200x faster
• 40-400x cheaper (w/ output tokens free)
• Frontier composable intelligence optimized for decisions
AFAICT the shortest path to AI-based economic revolution
32
44
773
70,138
Stagehand retweeted
you can build a price-monitoring tool on @browserbase in <5 minutes using fetch w proxies
running this for 3 products costs roughly $1.50 a day if i price-check every 15 minutes.
2
3
14
1,142
Introducing our Browser Agent Evals.
We benchmark frontier and open models using various harnesses on computer-use tasks.
Our evals are fully open source and reproducible via our Evals CLI.
10
11
35
6,638
Check out our evals and see how your favorite models and harnesses perform:
stagehand.dev/evals
3
219
Stagehand retweeted
We just made Astra's computer use 2.5x faster with Stagehand.
Astra works by executing code against the a11y tree, we built a translator that turns Astra's playwright commands into @Stagehanddev.
Astra chose to batch the entire logo into one command and one-shotted it.
GPT-6 Astra broke the internet with its ability to use blender and generate 3D worlds, all a byproduct of it's new computer use capabilities.
I dove into the source code and wrote about the loop that makes Astra so good:
12
14
157
24,509
