# browseragent.dev

> AI-optimized mirror of browseragent.dev containing 50 pages totalling 25,548 words of clean markdown content, structured data, and semantic HTML. Original source: https://browseragent.dev/. Last updated: 2026-05-01T14:35:29.882Z.

Each page is available as HTML (with JSON-LD structured data) and Markdown (text-only, ideal for LLMs and RAG).

## Homepage

- [The Way AI Uses the web.](/site-root.html): 78,000+ GitHub stars. Trusted by Fortune 500. The #1 open-source browser automation platform. (211 words)

## Articles & Blog Posts

- [Reagan Hsu](/team/reagan-hsu/index.html): Reagan Hsu, Founding Engineer at Browser Use. (69 words)
- [Our Mission: The Default Layer for Browser Automation](/posts/free-tier-announcement/index.html): How AI agents can authenticate autonomously to free, state of the art remote browsers. (458 words)
- [Luka Secilmis](/team/luka-secilmis/index.html): Luka Secilmis, Product & GTM Lead at Browser Use. (46 words)
- [Multi-Agent Scheduler](/templates/scheduler/index.html): Run multiple browser automation agents concurrently on configurable intervals (533 words)
- [The learning](/posts/bitter-lesson-agent-harnesses/index.html): Don't wrap the LLM. Don't wrap its tools either. (778 words)
- [Cloud Sandbox Boilerplate](/templates/sandbox/index.html): Cloud browser automation with @sandbox decorator for persistent auth and proxy routing (380 words)
- [Copy for LLM](/posts/prove-you-are-a-robot/index.html): For our agent-native signup we built a reverse-CAPTCHA that keeps humans out and lets agents in. (584 words)
- [Introducing BUX](/posts/bux-launch-blog/index.html): Browser Use Box (BUX) is a 24/7 remote VM with Claude Code and Browser Harness pre-installed, controlled from Telegram, the web, or SSH. (455 words)
- [Advanced Configuration](/templates/advanced/index.html): Full control over Browser Use agent behavior. (338 words)
- [Slack Bot for Browser Automation](/templates/slack/index.html): Execute browser automation tasks via Slack mentions with real-time session URLs. (300 words)
- [Magnus Müller](/team/magnus-muller/index.html): Magnus Müller, Co-Founder, CEO at Browser Use. (31 words)
- [Custom Tools](/templates/tools/index.html): Register custom tools that agents can invoke during task execution. (201 words)
- [Browser Use Boilerplate](/templates/default/index.html): Start automating browser tasks in seconds. (195 words)
- [Job Application Automation](/templates/job-application/index.html): Automate application submission with form filling and resume upload. (127 words)
- [LLM Arena](/templates/llm-arena/index.html): Compare AI models by executing identical tasks simultaneously. (203 words)
- [2FA Automation for Emails](/templates/agentmail/index.html): Automate account creation workflows with inbox and 2FA support. (157 words)
- [Automate Instacart](/templates/shopping-agent/index.html): A script for searching, selecting, and purchasing items on instacart. (74 words)
- [Share a Template](/templates/upload/index.html): Make websites accessible for AI agents. Extract interactive elements and automate browser interactions. (187 words)
- [Why abstractions break learning [Link to Why abstractions break learning](https://browser-use.com/posts/bitter-lesson-agent-frameworks#why-abstractions-break-learning)](/posts/bitter-lesson-agent-frameworks/index.html): All the value is in the RL'd model, not your 10,000 lines of abstractions. (1,333 words)
- [What's Next? [Link to What's Next?](https://browser-use.com/posts/one-year-of-progress#whats-next)](/posts/one-year-of-progress/index.html): One year after our first commit, we reflect on how far browser agents have come—and where they need to go next. (311 words)
- [Web Scraping in 2026](/posts/web-scraping-guide-2026/index.html): I tested the five most popular web scraping tools — Firecrawl, Bright Data, Cloudflare, Browserbase, and Browser Use — to help you pick the right one. (2,328 words)
- [A Brief Snapshot](/posts/how-to-win-hackathons/index.html): Winning hackathons is generally difficult, but there are some simple things you can do to place yourself above the rest. (1,420 words)
- [How we got here](/posts/two-ways-to-sandbox-agents/index.html): From AWS Lambda to Unikraft micro-VMs with a control plane architecture. (1,284 words)
- [Evaluation Challenges](/posts/speed-matters/index.html): 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. (828 words)
- [Training beats prompting. Every time. [Link to Training beats prompting. Every time.](https://browser-use.com/posts/agent-freedom#training-beats-prompting-every-time)](/posts/agent-freedom/index.html): Training beats prompting. Every time. (655 words)
- [Why stealth needs its own benchmark](/posts/stealth-benchmark/index.html): We built a stealth benchmark from real production data and tested every major cloud browser. (868 words)
- [100 hard browser tasks, one leaderboard](/posts/ai-browser-agent-benchmark/index.html): We benchmark every major LLM on 100 hard browser tasks. Browser Use Cloud scores 78%, 16 points ahead of the best open-source model.
 (607 words)
- [The cat & mouse game is about to get harder](/posts/bot-detection/index.html): How we built Browser Use to stay undetectable (943 words)
- [The results [Link to The results](https://browser-use.com/posts/what-model-to-use#the-results)](/posts/what-model-to-use/index.html): A statistically rigorous benchmark comparing the speed, cost, and accuracy of top frontier models for browser automation.
 (655 words)
- [How Parallel uses Browser Use](/posts/parallel/index.html): How Browser Use and Parallel AI are building the future of web search together.
 (318 words)
- [One API Key. That's It.](/posts/llm-gateway/index.html): 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? (360 words)
- [The Problem](/posts/frigade/index.html): How Frigade uses Browser Use to build AI-powered onboarding that understands any product.
 (430 words)
- [Kepler and Agent Score](/posts/new-generation/index.html): How New Generation uses Browser Use to score e-commerce sites for agent readiness.
 (257 words)
- [legal/terms-of-service/index.html](/legal/terms-of-service/index.html) (1 words)
- [changelog/index.html](/changelog/index.html) (1 words)
- [Blog](/posts/index.html): Read the latest updates, technical insights, and news from the Browser Use team. (727 words)
- [Cookie Syncing](/posts/web-agent-authentication/index.html): A comprehensive guide to logging AI web agents into your accounts — from syncing browser profiles to handling 2FA codes. (1,552 words)
- [The Benchmark](/posts/online-mind2web-benchmark/index.html): 97% on Online-Mind2Web benchmark. The highest score ever.
 (700 words)
- [Privacy Policy](/privacy/index.html): Make websites accessible for AI agents. Extract interactive elements and automate browser interactions. (3,084 words)
- [Pricing](/pricing/index.html): Transparent pricing for Browser Use. Start for free or subscribe to unlock more sessions and features. (197 words)
- [Templates](/templates/index.html): Create and share templates made by the Browser Use community to automate the web. (156 words)
- [Careers](/careers/index.html): Make websites accessible for AI agents. Extract interactive elements and automate browser interactions. (276 words)
- [SOC 2](/security/soc2/index.html): Browser Use is SOC 2 Type II compliant. Learn about our security practices, audits, and commitment to protecting your data. (167 words)
- [Stealth Browsers](/stealth-browsers/index.html): Undetectable browser infrastructure with anti-detect fingerprinting, automatic CAPTCHA solving, and residential proxies in 195+ countries. (131 words)
- [Global Proxy Network](/proxies/index.html): High-quality residential proxies in 195+ countries. Set a country code and go. Bring your own proxy for full control. (95 words)
- [Browser Automation,  Simplified](/web-agents/index.html): The easiest browser automation. Get structured outputs from any website with simple instructions. Run thousands of browser agents in parallel. (161 words)
- [Browser Use Box](/bux/index.html): Your 24/7 cloud agent. Claude Code and Browser Harness preinstalled. Drive it from Telegram, the web, or SSH. (145 words)
- [Web Agent LLMs](/custom-models/index.html): Purpose-built LLMs for browser automation. 4x faster than competing computer use models at the same accuracy, at a fraction of the cost. (97 words)
- [Browser Use Benchmarks](/benchmarks/index.html): Benchmarks comparing Browser Use web agent accuracy and browser stealth against other automation frameworks and cloud providers. (134 words)

## Resources

- [Full Page Index](/index.html): Browse all cached pages with rich metadata
- [About This Cache](/content/about.html): Methodology, technical details, and usage guidelines
- [XML Sitemap](/content/sitemap.xml): Machine-readable sitemap for crawler discovery
- [Robots.txt](/content/robots.txt): Crawler directives