Can I use my own proxies?

Yes. You can configure residential proxies, rotating proxy pools, and custom proxy authentication. The platform includes built-in proxy rotation and IP management features.

What automation frameworks are supported?

Native support for Playwright, Puppeteer, Selenium, and the proprietary Stagehand SDK. All work out-of-the-box with the cloud infrastructure.

Is on-prem deployment available?

No, Browserbase is cloud-first. For enterprise, they offer private cloud options, VPC connectivity, and data residency controls to meet security and regulatory requirements.

How does the Model Gateway work?

Your Browserbase API key grants access to major LLMs (like GPT-4, Claude) via the Stagehand framework. It provides unified billing and allows switching models without code changes.

What is the difference between the Fetch API and Browser API?

The Fetch API quickly retrieves page content (HTML, JSON, markdown) as clean data via a proxy network, ideal for context gathering. The Browser API gives you a full, programmable browser session to interact with dynamic pages and perform actions.

How does concurrency work in the pricing?

Concurrency refers to the number of browser sessions you can run simultaneously. The Free plan has 3, Developer 25, Startup 100, and Scale is custom. Browser hours are the total runtime for all your sessions combined.

Directory/Automation/AI Assistants/Browserbase

Browserbase

Browserbase is a complete platform for building and deploying AI agents that interact with the web. It provides cloud-hosted browser instances, web search, page fetching, and access to major LLMs through a single API key. Key capabilities include programmable browser sessions, search and fetch APIs, identity management for authenticating agents, a scalable runtime, and integrated observability for debugging. Target users are developers and founders building browser-based agents, automation workflows, data extraction pipelines, and end-to-end tests. It supports major automation frameworks like Playwright, Puppeteer, and Selenium, and integrates with AI agent frameworks like LangChain and CrewAI. Use cases span healthcare, finance, legal, and general business operations.

Automation

Visit website

Added on

Sep 22, 2026

Cloud BrowsersWeb Search APIFetch APIAgent IdentitySandbox RuntimeModel GatewayStagehand SDKObservabilityCustom ProxiesAuto CAPTCHA Solving

Product information

Everything worth knowing about Browserbase

The complete picture — from everyday features to the technical detail builders and IT folks dig for.

Core features

What it actually does

Cloud Browsers for Agents

Give your agents access to fleets of headless browsers to navigate and interact with websites like a human, handling logins and dynamic content.

Web Search & Fetch APIs

Let agents quickly find relevant websites with a single query (Search) and retrieve clean page content as HTML, JSON, or markdown (Fetch).

Agent Identity & Stealth

Enable agents to authenticate and bypass CAPTCHAs on sites using dedicated stealth research and strategic partnerships (e.g., Cloudflare).

Scalable Runtime

Deploy and run agents on Browserbase with scalable, sandboxed environments for faster and more secure execution.

Observability & Debugging

Unified debugging across session replays, logs, and prompts to monitor and fix agent workflows.

Technical capabilities

Stagehand AI Framework

The AI SDK for browser agents, offering natural language selectors, self-healing actions, and integration with major LLMs and agent frameworks like LangChain and CrewAI.

Model Gateway

A single API key provides access to major LLMs (e.g., via the Stagehand SDK) with unified billing and the ability to switch models without code changes.

Must watch videos

LangChain CEO Harrison Chase on the infrastructure bet he got wrong

51:58

Tutorial51:58

LangChain CEO Harrison Chase on the infrastructure bet he got wrong

- Chase (Co-Founder & CEO of LangChain) has rebuilt his product stack four times since 2022, chasing models that kept changing underneath him. In this episode of Navigators, Paul sits down with him to talk about what LangChain got right, and the one piece of infrastructure it built years too late. Harrison admits the team underestimated how massive the demand for raw inference would become, and how big general-purpose coding agents would get. He walks through the shift from LangChain to LangGraph to DeepAgents, why sub-agents rarely work the way people expect, and why LangChain now runs its own hiring, content, and coding work through internal agents exposed in Slack. Topics covered: - The gateway LangChain should have built a year earlier - Why agent capability converging on human capability changes the tools debate - Code mode: why agents writing code beats agents using human-style tools - Running GTM, content, and coding agents entirely inside Slack - Why sub-agents need to own whole tasks, not small pieces - The agent identity problem: delegated access vs. service accounts - Why LangChain's own AI slop problem got bad enough to need a Slack emoji --- Navigators is a series by Browserbase where we sit down with AI leaders navigating the future of what's happening in AI today. Host: Paul Klein (@pk_iv), founder, Browserbase Guest: Harrison Chase (@hwchase17), co-founder and CEO, LangChain Browserbase: https://browserbase.com LangChain: https://langchain.com

Agents will use the internet - Navigate 2026 Keynote

18:25

Tutorial18:25

Agents will use the internet - Navigate 2026 Keynote

A $5 Billion Fintech company CEO on the framework behind every product decision

41:42

Tutorial41:42

A $5 Billion Fintech company CEO on the framework behind every product decision

Immad Akhund (Co-Founder & CEO of Mercury) uses what he calls the cosmic cube to decide what Mercury builds next: one axis for customer type, one for product, one for compliance and infrastructure. In this episode of Navigators, Paul sits down with him to talk about why that space is functionally infinite, and why trying to expand into all of it at once is how companies lose. Immad also explains the two-year mistake of waiting to launch a corporate credit card, why he treats every new product like a fresh seed-stage startup inside Mercury, and why talent, not capital, is the real limit on how many bets the company can run at once. CHAPTERS: 00:00 Why 1-on-1s stopped working once he was managing execs 07:34 Agentic cards: letting AI spend on your behalf 11:09 Why fintech is three times harder than software 13:50 Chewing glass: getting bank-charter ready 16:08 Reaching the edge of knowledge in six months 28:26 Killing 1-on-1s and what Jensen Huang has to do with it 36:39 The "cosmic cube": how Mercury picks its next bet --- Navigators is a series by Browserbase where we sit down with AI leaders navigating the future of what's happening in AI today. Host: Paul Klein (@pk_iv), founder, Browserbase Guest: Immad Akhund (@immad), co-founder and CEO, Mercury Browserbase: https://browserbase.com Mercury: https://mercury.com

Who uses it

Real use cases, no hype

Build Browser Agents

Power AI agents that navigate complex, login-protected web apps autonomously.

Automated Web Testing

Run end-to-end tests in isolated, scalable browser environments to catch broken flows.

Large-Scale Data Extraction

Scrape and extract structured data from any website at scale, bypassing CAPTCHAs and blocks.

Workflow Automation

Automate tedious multi-step forms, job applications, and data entry across web portals.

Price & Content Monitoring

Track competitor prices, job listings, and content changes across thousands of sites in parallel.

Research at Scale

Spin up concurrent browser sessions for massive web research and real-time analysis.

Integrate AI with the Web

Bridge AI models (LangChain, CrewAI, etc.) to real-world web interactions via a single API.

What's great

Full-featured platform for browser agents: cloud browsers, search, fetch, runtime, model gateway.
Zero setup. Spin up a browser, connect your model, and run tasks immediately.
Integrated stealth and captcha solving for reliable web navigation.
Native compatibility with Playwright, Puppeteer, Selenium, and the Stagehand AI SDK.

Technical strengths

Unified observability with session replays and logs for debugging.
Advanced proxy rotation and IP management built-in for large-scale scraping.
Model Gateway allows using any major LLM with a single API key and unified billing.

Where it falls short

Costs can escalate quickly with heavy usage; browser hour pricing is key.
Free plan is very limited (1 browser hour, 3 concurrent browsers).
On-prem deployment not offered; it's a cloud-first platform.

Technical limitations

Data retention is limited to 7 days on the Free plan.
Advanced stealth mode requires Scale plan or custom pricing.

For technical folks

The deep-dive specs

FAQ

Includes technical Q&A

It's a platform for building and deploying agents that browse the web like humans. It provides cloud browsers, search/fetch APIs, a sandbox runtime, identity (stealth/captcha solving), a model gateway for LLMs, and observability tools—all under one API key.