give your agents access to the whole web - creators of @stagehanddev & @trydirector
Joined February 2024
- Tweets 848
- Following 54
- Followers 20,097
- Likes 2,396
151 Photos and videos
Pinned Tweet
Jun 11
We’re launching the conference for the best teams shipping agents: Navigate 2026 🌎
Join us on Sept 10th in SF for:
→ Keynotes and firesides from Anthropic, Vercel, Ramp, Modal, Okta, and more
→ Technical workshops from teams running agents at scale
→ Deep dives on evals, orchestration, memory, and the infra layer underneath it all
Register below 👇
23
12
141
81,889
Jun 11
We’re launching the conference for the best teams shipping agents: Navigate 2026 🌎
Join us on Sept 10th in SF for:
→ Keynotes and firesides from Anthropic, Vercel, Ramp, Modal, Okta, and more
→ Technical workshops from teams running agents at scale
→ Deep dives on evals, orchestration, memory, and the infra layer underneath it all
Register below 👇
23
12
141
81,889
Jun 11
We have an incredible lineup of speakers joining us on stage:
> Matt Ubl, CTO, @Vercel
> Monica Bajaj, SVP, @Okta
> Thariq Shihipar (@trq212), building Claude Code, @AnthropicAI
> Erik Bernhardsson (@bernhardsson), CEO, Modal
> Mike Luo, Eng Lead, @TryRamp
> Yash Patil (@ypatil125), CEO, @AppliedCompute
> Ian Livingstone (@ianlivingstone), CEO, @KeycardLabs
> Rob Ferguson, VP Technology, @FireworksAI_HQ
> Paul Klein, CEO, @Browserbase
and so many more!
1
19
4,587
Jun 10
Excited to partner with Anthropic on Managed Agents,
The Browse CLI gives your agents reliable access to the web for advanced tasks.
Read the full documentation below.
New from Code with Claude Tokyo: scheduled deployments and environment variables in vaults are in public beta in Claude Managed Agents, and dynamic workflows in Claude Code are generally available.
Agents now run on a schedule, use your tools securely, and take on bigger jobs.
6
5
57
13,315
Browserbase retweeted
Jun 9
Claude Fable 5's computer use blows other foundation models out of the water.
On our custom task set it scores 7.3% higher than 4.8 while also being more cost efficient than sonnet 4.5.
Our hybrid agent built into Stagehand significantly outperformed the native CUA harness.
Introducing Claude Fable 5: a Mythos-class model that we’ve made safe for general use.
Its capabilities exceed those of any model we’ve ever made generally available.
2
7
26
3,864
Jun 8
Your agents shouldn't relearn how to use sites every time they visit.
Browse.sh is the web skills catalog for your agents. Since launching 2 weeks ago the community contributed over 300 skills and 35,000 CLI downloads.
We're 2nd on Product Hunt, help us win product of the day!
25
20
176
39,127
Jun 5
Are LLMs actually good enough to fully automate scientific research?
If you're an engineer or researcher, we're hosting a panel with lead researchers from Microsoft and Nvidia on June 16th at the Browserbase office.
Apply to attend below!
6
1
23
3,327
Browserbase retweeted
Jun 4
Stagehand just crossed 1 Million weekly downloads, but we're not done yet.
New in our latest 3.5.0 release:
- native clipboard API
- screenshots in extract()
- better snapshots & local mode use
6
3
40
10,783
Jun 4
Most companies view new model releases as a threat to their existence.
Browserbase only improves as labs release better models.
Our customers get more out of our infrastructure, and stay ahead of the bleeding edge of AI.
3
2
30
13,356
Jun 3
See how your favorite models perform on our computer use evals,
We found that Opus 4.8 is the most accurate on our eval set, beating out leading models from OpenAI and Gemini.
Jun 3
Introducing the new Stagehand Evals,
We've been working closely with labs evaluating their latest models on custom tasks that represent real, production use cases.
Excited to push forward the frontier and ensure our customers use the model best for them.
4
2
23
4,813
Jun 3
Picking the wrong API for browser automation makes your system slower, more expensive, and harder to debug.
We wrote a blog explaining how the best AI teams use our Search, Fetch, and Browser APIs effectively.
5
3
38
7,264
Jun 2
You can't just give a model the ability to run CDP commands and expect it to perform well in production.
Real browser agents need a harness that provides security, identity, caching, credential brokering, and memory.
Read about how we think about the browser agent harness.
6
2
22
2,851
Jun 1
Building Browser Agents has never been easier.
Join us this Thursday (6/4) for an Opus 4.8 webinar with @AnthropicAI and @Letta_AI.
We'll discuss how we evaluate model capabilities with Stagehand and show a live demo on how to power your own agentic products with Browserbase.
5
6
36
6,348