Stagehand

What is Stagehand?

Stagehand is an SDK for browser agents, published by Browserbase and available for TypeScript, Python and Go. You mix ordinary code with natural-language calls: act performs an action on a page, extract pulls structured data against a schema, and observe inspects what can be done. The browser can be a Browserbase cloud session, a browser launched on your machine, or any Chromium instance you attach to over CDP. Any large language model works, including OpenAI, Anthropic and Google models, and an optional Model Gateway can pick a model for each call using only your Browserbase key. Server-side caching reuses recorded actions to cut repeat inference. The SDK is installed with npm install @browserbasehq/stagehand and is listed as MIT-licensed open source. The pricing page we reviewed returned a 404, so hosted Browserbase browser costs are not covered here.

Use cases

• Extract structured data from websites
• Automate web forms and workflows
• Build browser agents in TypeScript
• Build browser agents in Python
• Run natural-language steps in web tests
• Control browsers in local or cloud sessions

Who it's for

• TypeScript developers
• Python developers
• Go developers
• AI engineers

Why use Stagehand

• Combining code and plain-language instructions gives you precise control where you need it and flexibility elsewhere.
• Switching between OpenAI, Anthropic and Google models is a configuration change.
• Caching reuses recorded actions, which avoids paying for the same LLM call twice.
• You can develop against a local browser and move to Browserbase cloud browsers for production scale.
• The SDK is available in three languages, so it fits your existing stack.

Stagehand features

• act, extract and observe calls on web pages
• Structured extraction with schemas
• SDKs for TypeScript, Python and Go
• Browserbase cloud, local or CDP-attached browsers
• Use any LLM, with per-call model overrides
• Model Gateway with automatic model selection
• Server-side caching of repeated actions
• Browserbase regions in the US, Frankfurt and Singapore
• Setup prompt for coding agents

Stagehand integrations

• Browserbase
• OpenAI
• Anthropic
• Google

How to get started with Stagehand

1. Install the SDK, for example with npm install @browserbasehq/stagehand.
2. Get a browser from browserbase.launch, localBrowser.launch or localBrowser.connect.
3. Call Stagehand.create with the browser, and optionally a model and API key.
4. Use act, extract and observe with plain-language instructions and schemas.
5. Turn on the cache option and choose cheaper models for simple steps to lower costs.

Stagehand limitations

• Model Gateway and server-side caching require Browserbase-hosted browsers
• Model Gateway rejects stopSequences, so pin a model with its own key when you need them
• Hosted Browserbase browsers are a separate service from the SDK
• Requires writing code to use

Stagehand pricing

Stagehand is open source, so you can use and self-host it for free.

Prices can change and may vary by country or exclude tax. Check the official pricing page.

Stagehand alternatives

The main Stagehand alternatives listed on Debuly are Browser Use, Playwright, Browserbase, Hyperbrowser, Marvin and Moli. The table compares pricing and platforms; order is A–Z.

1. 

   Browser Use

   Cloud browsers and hosted web agents for AI, plus an MIT-licensed open-source browser agent, billed pay-as-you-go from $0.02 per hour.

   Developer platformsAutomation and agentsCoding
   PaidVisit Browser Use (official site)
2. 

   Browserbase

   Cloud platform of headless browsers, search and fetch APIs and agent runtime for building AI agents that browse and act on the web.

   Developer platformsAutomation and agentsCoding
   FreemiumVisit Browserbase (official site)
3. 

   Hyperbrowser

   Cloud infrastructure that gives AI agents hosted Chrome sessions, isolated sandboxes, and web fetch, crawl and search APIs.

   Developer platformsAutomation and agentsCoding
   FreemiumVisit Hyperbrowser (official site)
4. 

   Marvin

   Open source Python framework from Prefect for getting structured output from LLMs and building agent workflows from tasks and threads.

   Developer platformsCodingAutomation and agents
   Open sourceVisit Marvin (official site)
5. 

   Moli

   Open-source browser engine from Lexmount that lets AI agents extract web content and automate pages with low memory use.

   Developer platformsAutomation and agentsCoding
   Open sourceVisit Moli (official site)
6. 

   Playwright

   Open-source Microsoft framework for end-to-end web testing and browser automation across Chromium, Firefox and WebKit, with CLI and MCP for agents.

   Developer platformsCodingAutomation and agents
   Open sourceVisit Playwright (official site)

Stagehand FAQ

Sources & verification

Facts on this page come from the official sources below, each with the date we read it. Written by Debuly; the vendor did not review this page.

Image credits

• Logo: from stagehand.dev · fetched 23 Oct 2026 · Vendor trademark, used only to identify the product; removed on request
• Cover: none collected yet, so a generated tile is shown.

Spot an error? Report an issue with this listing. We also remove a logo or image on the owner's request.