How much does Stagehand cost?

Free and open source (MIT); Browserbase infrastructure and model tokens are billed separately when used.

Does Stagehand support MCP and tool calling?

Full under the Agentic Index verification standard. Stagehand publishes public evidence of Model Context Protocol (MCP) support, tool calling, and API or SDK extensibility for connecting agents to external tools. Evidence basis: Stagehand is an MIT licensed SDK for TypeScript, Python and Go, with a published reference for the Stagehand, context, page, locator and response objects. Its browser tools (run, snapshot, screenshot) can be exposed to agent frameworks over. Graded from public evidence only against the Agentic Index 14 point capability taxonomy. No vendor pays for placement.

Can Stagehand be self hosted or run in a private VPC?

Full under the Agentic Index verification standard. Stagehand publishes public evidence of self hosted or private VPC deployment, along with data residency options for controlling where agent data is processed and stored. Evidence basis: The MIT licensed library runs wherever the customer runs it, against a browser launched on the customer's own machine or any Chromium browser attached over CDP, with Browserbase's cloud as one option among three. Graded from public evidence only against the Agentic Index 14 point capability taxonomy. No vendor pays for placement.

Can you bring your own model or route between providers with Stagehand?

Full under the Agentic Index verification standard. Stagehand publishes public evidence of bring your own model and bring your own key (BYOK), and of routing tasks between models or providers rather than being locked to one. Evidence basis: The SDK's model option pins a model from providers such as OpenAI and Anthropic and, with the customer's own API key, calls that provider directly. A client side LLM callback brings any model. Omitting the model routes through Browserbase's. Graded from public evidence only against the Agentic Index 14 point capability taxonomy. No vendor pays for placement.

Back to vendors

Stagehand

Q: Who is Stagehand for?

developers building browser agents, teams needing production reliable automation, engineers replacing brittle selector scripts

Q: What are the best alternatives to Stagehand?

Based on documented capability coverage across the Agentic Index 14 point taxonomy, the closest alternatives to Stagehand among browser and computer-use agents are Axiom.ai, AgentQL, Notte, Autotab. Each is graded on the same public evidence, and no vendor pays for placement.

Also known as: Stagehand SDK, stagehand.dev, Browserbase Stagehand

Visit site

Browser / computer-use agentfirst party productVerified 2026-09-27

Entry priceFree and open source (MIT)Full pricing detail

MIT licensed browser automation SDK from Browserbase for TypeScript, Python and Go: natural language act, extract and observe steps mixed with Playwright style code, on a local, attached or Browserbase browser, with the model the developer picks. v4 leaves orchestration to your code.

Stagehand is an MIT licensed browser automation SDK built by Browserbase for TypeScript, Python and Go. It gives developers two layers of control in the same script: AI primitives (act to carry out an instruction, extract to pull structured data against a schema, observe to discover the actions available on a page) that heal when a site's markup changes, and Playwright style page methods (goto, click, type, locator, screenshot) for deterministic steps. It drives a browser launched locally, any Chromium browser attached over CDP, or a Browserbase cloud browser.

Version 4 removed the built in agent() loop: Stagehand now exposes discrete tools and leaves control flow to the developer's code or agent framework, with experimental integrations that hand a Stagehand browser to CrewAI, Deep Agents, Mastra, the Vercel AI SDK, Eve, Claude Code and Codex. The developer pins a model with their own provider key or a custom LLM callback, or lets Browserbase's Model Gateway choose one. Browserbase's hosted services around it, such as cloud browsers, the managed action cache, session replay and Model Gateway, are Browserbase products, billed by Browserbase and scored on its own profile.

Vendor details

Canonical URL

https://www.stagehand.dev

Funding status

A product of Browserbase; open source under the MIT license

Company status

first party product

Use cases & customers

Target customers

developers building browser agentsteams needing production reliable automationengineers replacing brittle selector scripts

Deployment options

local browserany Chromium browser over CDPBrowserbase cloud browser

Integrations

Experimental integrations with CrewAI, Deep Agents, Mastra and the Vercel AI SDK over MCP, Eve natively, and guides for Claude Code, Codex, fx and Pi; runs on local Chromium, any CDP browser or Browserbase.

In practice

Your Playwright scripts break every time the site ships a redesign. Stagehand resolves instructions like click the submit button at runtime through AI rather than a hardcoded selector.

A fully autonomous agent is too unpredictable for production but pure code is too brittle. Stagehand lets you use natural language for unfamiliar pages and deterministic code where you already know the flow.

You want to see what the AI intends before it acts. Actions can be previewed before running and cached once resolved, turning an exploratory run into a repeatable workflow that costs fewer tokens.

Sources & related URLs

Research sources

https://www.stagehand.dev/ https://docs.stagehand.dev/v4/first-steps/introduction https://docs.stagehand.dev/v4/migrations/v3 https://docs.stagehand.dev/v4/configuration/models https://github.com/browserbase/stagehand

Agentic Index coverage score

7.0 / 14 capabilities · 50%

Integrations & Tool Calling	Partial
Experimental integrations give agents in CrewAI, Deep Agents, Mastra, the Vercel AI SDK, Eve, Claude Code and Codex a Stagehand browser, but Stagehand itself has no connectors or tool route. Its docs state v4 includes no autonomous agent or general purpose MCP client, and third party tools are called from the developer's own code. Sourcedocs.stagehand.dev/v4/best-practices/mcp-integrationsread 2026-09-27
Workflow Orchestration	Partial
Stagehand v4 removed agent(). Its docs say the built in orchestrator is gone and v4 exposes discrete tools, leaving the control flow to the developer's code or agent framework. The act, extract and observe calls are single steps within that flow. Sourcedocs.stagehand.dev/v4/migrations/v3read 2026-09-27
Knowledge Grounding & RAG	Not documented
The extract() call pulls structured data from the page in view with a schema, which is run time web work. No retrieval index over the customer's own knowledge is part of the SDK. Sourcedocs.stagehand.dev/v4/basics/extractread 2026-09-27
Human Oversight & Guardrails	Partial
The developer decides which steps use AI and which run as deterministic code, and observe() returns candidate actions that code can inspect before calling act(). That is control the customer keeps, but no approval step for a person before an action commits is documented. Sourcedocs.stagehand.dev/v4/basics/observeread 2026-09-27
Security, Identity & Governance	Not documented
No access model or attestation of Stagehand's own is published. The roles, SSO and SOC 2 Type II that apply when it runs on Browserbase belong to Browserbase. Running locally keeps data on the customer's machine. Sourcedocs.stagehand.dev/v4/first-steps/introductionread 2026-09-27
Observability & Auditability	Partial
The SDK reports token usage and performance metrics (stagehand.metrics()) and configurable logs on a local browser. Live views, recordings and session replay come from Browserbase, and no trace or audit trail of the SDK's own is documented. Sourcedocs.stagehand.dev/v4/configuration/observabilityread 2026-09-27
Memory & State Persistence	Not documented
In v4, action caching is Browserbase Cache, a server side layer that works only on a Browserbase browser. With a local browser every call runs inference, and persisted user data is browser state. No memory the SDK keeps for an agent is documented. Sourcedocs.stagehand.dev/v4/best-practices/cachingread 2026-09-27
Deployment & Data Residency	Full
The MIT licensed library runs wherever the customer runs it, against a browser launched on the customer's own machine or any Chromium browser attached over CDP, with Browserbase's cloud as one option among three. Sourcedocs.stagehand.dev/v4/configuration/browserread 2026-09-27
Prebuilt Agents, Templates & Packs	Partial
Stagehand ships AI rules files for coding agents, use case guides (such as observe use cases) and migration guides, which are starting points a developer builds from. No catalog of prebuilt automations or agents is documented, and Director is a separate Browserbase product. Sourcedocs.stagehand.dev/v4/first-steps/ai-rulesread 2026-09-27
Triggers & Channel Coverage	Not documented
The library runs only when the customer's code calls it. The deployment guide puts it behind the customer's own Vercel endpoint and cron, and no schedule, event or inbound trigger of Stagehand's own is documented. Sourcedocs.stagehand.dev/v4/best-practices/deploymentsread 2026-09-27
Model Flexibility & Routing	Full
The SDK's model option pins a model from providers such as OpenAI and Anthropic and, with the customer's own API key, calls that provider directly. A client side LLM callback brings any model. Omitting the model routes through Browserbase's Model Gateway. Sourcedocs.stagehand.dev/v4/configuration/modelsread 2026-09-27
APIs, SDKs & MCP Extensibility	Full
Stagehand is an MIT licensed SDK for TypeScript, Python and Go, with a published reference for the Stagehand, context, page, locator and response objects. Its browser tools (run, snapshot, screenshot) can be exposed to agent frameworks over MCP. Sourcedocs.stagehand.dev/v4/reference/stagehandread 2026-09-27
Testing, Debugging & Optimization	Partial
Logs, metrics and self healing actions help developers debug runs. The evaluations page belongs to the v3 docs, and no evaluation harness or scored tests are documented for v4. Sourcedocs.stagehand.dev/v4/configuration/loggingread 2026-09-27
Browser & Computer Use	Full
Stagehand drives a real Chromium browser, launched locally, attached over CDP or hosted on Browserbase, through natural language act, extract and observe calls mixed with Playwright style page methods (goto, click, type, locator, screenshot) in TypeScript, Python and Go. Sourcedocs.stagehand.dev/v4/first-steps/introductionread 2026-09-27

The Agentic Index coverage score grades every vendor Full, Partial or Not documented against the same 14 buyer facing capabilities, from public evidence only. Each capability links to how all vendors in the index score on it. How this evidence is graded

Pricing

Free and open source (MIT)

free library; Browserbase infrastructure and model tokens billed separately

Free tier

What is public

The MIT license and full source are public; Browserbase publishes its own infrastructure prices separately.

Billing mechanics

Stagehand carries no license cost at all. Running locally, the only spend is model tokens from whichever provider the developer uses. Moving to Browserbase adds metered browser hours and proxy bandwidth, and unlocks concurrent sessions, stealth mode, session replay, CAPTCHA solving, Agent Identity and a Model Gateway that consolidates model access under one API key.

Cost watchouts

Three separate invoices are easy to miss: browser time on Browserbase, LLM tokens from your model provider, and proxy bandwidth. The framework being free does not make the workload free.

Variable cost rationale

Local use costs only model tokens, and action caching directly reduces that, but hosted use adds browser hours and proxy bandwidth metered by consumption, and an agent exploring unfamiliar pages consumes all three simultaneously.

Additional watchouts

The framework being free is not the same as the workload being cheap. Model tokens dominate cost for AI resolved actions. In v4, action caching is a Browserbase service, so on a local browser every call runs inference and repeated steps pay again to resolve the same selectors.

Overage / add-ons

On Browserbase, browser hours beyond the plan allowance are reported at $0.12 per hour and proxy bandwidth at $12 per GB beyond the first gigabyte

Sales call required

No, self serve available

Free / trial

Free under the MIT license with no usage limits

Commercial notes

Stagehand is open source used as distribution for paid infrastructure. Giving the framework away with genuine local capability builds adoption. The paid Browserbase infrastructure captures the moment a workload needs concurrency, stealth or proxy rotation, which is precisely when it becomes production.

Key ambiguities

Stagehand itself has no price. The figures that matter belong to Browserbase, which publishes its infrastructure prices separately, and they are not quoted here.

Missing data

Browserbase's current tier structure and rates, and whether Model Gateway usage carries a margin over direct provider pricing.

Agentic Index verified 2026-09-27

Official pricing page

Related vendors

Alternatives to Stagehand

The closest documented capability profiles to Stagehand among browser and computer-use agents tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.

Axiom.ai10.0 / 14Adds documented Triggers & Channel Coverage
AgentQL5.5 / 14Adds documented Triggers & Channel Coverage
Notte9.5 / 14Adds documented Security, Identity & Governance and Triggers & Channel Coverage
Autotab8.0 / 14Adds documented Memory & State Persistence and Triggers & Channel Coverage
Brave Leo AI Browsing6.0 / 14Adds documented Knowledge Grounding & RAG and Memory & State Persistence
Browserbase10.0 / 14Adds documented Security, Identity & Governance and Memory & State Persistence, among others

Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded

Compare Stagehand with other vendors →Compare all browser and computer-use agents →See where Stagehand ranks →

Data confidence: high