Browser Use - Enable AI to control your browser
Blog
Updates, insights, and news from the team.
All Posts
Engineering
How We Built Secure, Scalable Agent Sandbox Infrastructure
From AWS Lambda to Unikraft micro-VMs with a control plane architecture.
Larsen CundricFeb 25, 2026
Engineering
How we built scalable evaluation infrastructure for AI web agents
A deep dive into our highly scalable LLM-as-a-judge evaluation platform that solves web agent variance.
Alexander YueFeb 23, 2026
Engineering
What LLM model should I use for Browser Use? The Definitive Browser AI Benchmark
A statistically rigorous benchmark comparing the speed, cost, and accuracy of top frontier models for browser automation.
Alexander YueFeb 19, 2026
Customers
How Browser Use Empowers Frigade to Build the Best Onboarding Agent
How Frigade uses Browser Use to build AI-powered onboarding that understands any product.
Reagan HsuFeb 6, 2026
Engineering
Browser agent bot detection is about to change
How we built Browser Use to stay undetectable
Aitor MatoFeb 2, 2026
Engineering
Browser Agent Benchmark: Comparing LLM Models for Web Automation
We compiled our learnings from AI browser agent evaluations into an open-source benchmark for model comparison.
Alexander YueJan 31, 2026
Customers
Browser Use <> Parallel AI - The Future of Web Search
How Browser Use and Parallel AI are building the future of web search together.
Reagan HsuJan 27, 2026
Engineering
The Bitter Lesson of Agent Frameworks
All the value is in the RL'd model, not your 10,000 lines of abstractions.
Gregor ZunicJan 16, 2026
Announcements
Celebrating One Year of Progress in Browser Agents
One year after our first commit, we reflect on how far browser agents have come—and where they need to go next.
Gregor ZunicNov 12, 2025
Engineering
Speed Matters: How Browser Use Achieves the Fastest Agent Execution
Matching state-of-the-art accuracy is table stakes. We built BU 1.0 to be the fastest browser agent while maintaining the same performance.
Gregor ZunicOct 9, 2025
Product
The Fastest Web Agent in the World
We built a special LLM gateway that reduces the latency by 6x while keeping the same performance. The agents can now take 20 steps per minute. How many can a human do?
Gregor ZunicOct 8, 2025
Product
Stealth Infrastructure
Introducing: Stealth and native browser use infrastructure built directly into the library. Want to bypass Cloudflare, or any other anti-bot protection? It's never been easier đź‘€
Gregor ZunicSep 30, 2025
Engineering
Closer to the Metal: Leaving Playwright for CDP
Placeholder description
N
Nick SweetingAug 20, 2025
Announcements
We Raised $17M to Build the Future of Web for Agents
How a weekend project turned into the largest open-source browser automation framework—and why we're just getting started.
Gregor ZunicMar 22, 2025
Engineering
Browser Use = state of the art Web Agent
Browser Use achieves state-of-the-art performance on the WebVoyager benchmark with an 89.1% success rate.
Gregor ZunicDec 15, 2024