Notte logo

Notte

Freemium
訪問

Notte is browser infrastructure for AI agents and production web automation. It provides managed cloud browsers, AI-driven workflows, developer interfaces, and operational tools for authenticated or recurring web tasks.

Notteとは?

Notte is a browser infrastructure platform for AI agents and production web automation. It provides isolated cloud browser sessions, AI browser agents, serverless browser functions, and developer access through Playwright, Puppeteer, Selenium, or CDP. Teams can use it to operate websites through a real browser when a stable API is unavailable, including for dynamic-page extraction, authenticated workflows, QA, and browser-backed APIs.

A typical workflow starts a Notte cloud browser session, then controls it with Notte actions, an AI agent, or an existing automation library. Profiles can preserve browser state across runs, while credential vaults keep authentication data out of application code. Proxy routing, CAPTCHA handling, live views, replays, and observability support workflows that need more than a locally managed browser.

Notteでできること

Managed cloud browser sessions

Run isolated Chromium sessions on Notte’s cloud infrastructure, with concurrency and session-duration limits that vary by plan.

AI browser agents

Describe a web task in natural language and let an agent navigate and extract information without maintaining selectors for each workflow.

Browser functions

Package browser automations as callable or scheduled serverless functions colocated with the browser runtime.

Authentication and persistent state

Use encrypted Vaults for credentials, Personas for verification emails and phone-based OTP workflows, and Profiles to reuse cookies, local storage, and authenticated browser state.

Developer tooling and compatibility

Connect Playwright or Puppeteer over CDP, and use Selenium-compatible access or Notte’s SDK with supported Python and TypeScript workflows.

Operations and protected-site tooling

Configure proxies and CAPTCHA handling, watch active sessions through live view, and inspect replay artifacts after a run.

利用シーン

“Authenticated portal automation”

Automate workflows that require sign-in, MFA, or persistent sessions, such as retrieving invoices, checking account information, or completing customer-portal tasks.

“Structured web research and extraction”

Navigate dynamic pages and return structured data for tasks such as product-price comparison, business-registry checks, market research, or public dataset discovery.

“Recurring browser jobs”

Convert a Playwright or Notte workflow into a Browser Function that can be invoked or scheduled for monitoring, downloads, QA checks, or other repeatable tasks.

“Browser-backed APIs”

Turn a site-specific workflow into an API endpoint, allowing an application to request normalized results without implementing the underlying browser navigation itself.

よくある質問

Can Playwright connect to Notte?

Yes. Playwright connects to a Notte cloud browser session over CDP, allowing existing Playwright scripts to control a managed browser. Notte documents Python and TypeScript connection examples.

How are credentials and logged-in browser state handled?

Credentials can be stored in Notte Vaults and retrieved at runtime rather than hardcoded. Profiles can preserve cookies, local storage, and other authenticated browser state for reuse in later sessions.

Can Notte workflows be deployed or scheduled?

Yes. Browser workflows can be packaged as serverless Browser Functions, which the site describes as callable and schedulable. The platform also presents recurring browser tasks as a supported use case.

What does Notte pricing depend on?

Notte uses credits and operational limits. The pricing page lists browser sessions, Browser Functions, residential proxies, and LLM tokens as usage-related components; plans differ in included credits, browser concurrency, agent or function concurrency, vault and profile capacity, and maximum session duration.

クイック情報

Category
Developer Tool
Primary purpose
Browser infrastructure for AI agents and web automation
Browser access
Cloud Chromium sessions with CDP access
Automation interfaces
Notte SDK, Playwright, Puppeteer, Selenium, and CDP
Authentication tools
Credential Vaults, Personas, and persistent Profiles
Pricing model
Credit-based plans with free, paid, and enterprise options

Notteの代替品

Steel logo

Steel

steel.dev

Steel is open-source browser infrastructure for AI agents and web automation. It provides cloud browser sessions through an API, with support for common browser automation tools and workflows such as scraping, research, RPA, and agent-driven web tasks.

Hyperbrowser logo

Hyperbrowser

www.hyperbrowser.ai

Hyperbrowser provides on-demand cloud browsers and sandboxes for AI agents, web automation, scraping, testing, and agentic code execution. It connects browser workflows through an API, Playwright, Puppeteer, Python, or Node.js.

Simular logo

Simular

www.simular.ai

Simular is an autonomous computer platform that uses AI agents to operate real computers and automate digital workflows. It serves individuals, builders, operators, and businesses that need to automate tasks across desktop applications and websites, including workflows that do not expose traditional APIs.

BrowserAct logo

BrowserAct

www.browseract.com

BrowserAct is a no-code AI web scraping and browser automation platform that builds reusable Bots from plain-language data requests. It helps teams collect structured, refreshed web data in the cloud or give local AI agents a browser layer for web tasks.

Apify logo

Apify

apify.com

Apify is a marketplace and platform for running web-scraping and browser-automation tools, called Actors. It helps developers and teams collect live web data, feed AI and data workflows, automate browser tasks, and connect runs to external tools.

Stagehand logo

Stagehand

www.stagehand.dev

Stagehand is an SDK for building browser agents with Playwright-style APIs, natural-language actions, structured extraction, and self-healing behavior. It supports TypeScript, Python, and Go for agents that need to operate web pages with browser-level control.