OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Agent Infrastructure

Browserbase

Browserbase provides cloud browser infrastructure for agents to navigate and interact with websites, with search and fetch capabilities, agent identity features, runtime environments, and tools for observing browser sessions.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Browserbase — OpenViST project profile in Agent Infrastructure.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Browserbase when an agent workflow requires browser-based website interaction, web search or retrieval, or visibility into browser sessions.

Who it is for

  • Teams building agents that need to browse and act on websites.
  • Developers creating web research or browser-automation workflows.

Documented uses

  • Navigate web pages and interact with site controls when direct APIs are unavailable.
  • Combine web search with page retrieval and browser interaction for research tasks.
  • Automate form completion and work with authenticated sites.
  • Observe browser sessions through logs, live views, and replay.
  • Run agent browser tasks in isolated runtime environments.
Before you choose

Requirements & limits

The official pricing page lists a free plan and paid plans. The homepage describes Browserbase's web capabilities as programmable like APIs.

  • Browser interaction is paired with search and fetch capabilities.
  • Session logs, live views, and replay support observation of browser activity.
  • Runtime environments and sandboxed sessions address agent execution needs.
  • The official pricing page lists both free and paid plans.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Search, fetch a page, and browse with Browserbase

Use one script to search the web, retrieve a page without a browser session, and interact with a page in a Playwright-controlled cloud browser.

Before you start

  • A Browserbase API key.
  • TypeScript or Python, as supported by the template.
  • Playwright for the browser-session portion.

Steps

  1. Create the getting-started template using the command for your chosen language: the command below for TypeScript, or uvx create-browser-app --template getting-started-with-browserbase for Python.

    Documented command
    npx create-browser-app --template getting-started-with-browserbase

  2. Run the script to use the Search API and print top results with titles and URLs, then fetch a Wikipedia page and extract its title from the raw HTML.

  3. Create a Browserbase session and connect to it via CDP using Playwright.

  4. Navigate to Wikipedia, search for a topic, and extract the article title, summary, and section headings.

Expected outcome

A script demonstrates Search API results, Fetch-based page retrieval, and browser interaction through a Playwright-connected Browserbase session.

Guide limitations

  • The template describes a getting-started example; it does not document production deployment or scaling steps.
  • Search and Fetch do not require a browser session; the interactive browser portion uses a Browserbase session.
  • The template does not specify API-key setup instructions.
Documentation 1 ↗
Evidence and transparency

Sources & review

Guide documentation ↗
Source record details
Source availability
Active
Sources checked
7 October 2026
Original website title
Browserbase | Browserbase · Official homepage title · retained in its source language
How we review sourcesSuggest a correction