Skip to content
ProductArena

Rank #4 of 7 in Browser Automation for Agents

Stagehand logo

Stagehand

Open Source Built-in AI assistant

Browserbase, Inc.

stagehand.dev ↗Try it →
PA Score28/100AGENT-READY51/100BUILT-IN AI69/100API0/100
MCP✓CLI—API✓
★ 24.3k▲ 9.8k/yrnpm 1.2M/wk★ +132npm/wk -253.2kpypi/wk -11.2k
ArenasBrowser Automation for Agents#4/7

Access

Open app ↗API docs ↗

Install

npmnpm install @browserbasehq/stagehand
pippip install stagehand

Compare head-to-head

Browser Use logovs Browser UseSkyvern logovs SkyvernHyperbrowser logovs HyperbrowserSteel logovs SteelNotte logovs NotteSmooth logovs Smooth

Alternatives to Stagehand →

Showcase

Stagehand homepage screenshot
homepage · captured Sep 2026 · view live ↗
Stagehand docs screenshot
docs · captured Sep 2026 · view live ↗

Products

Browserbase, product by product →

Browserbase ships more than one product — each judged line competes in its own arena on the same stories as everyone else.

LineArenaRankPA Score
BrowserbaseWeb Scraping APIs#5/827/100
Stagehandthis pageBrowser Automation for Agents#4/728/100

Try itExperimental

See what an agent can do with Stagehand before you ever sign up. Pick a story: recorded sessions replay real probe-harness transcripts; sandboxed self-drive sessions are designed and gated (docs/TRY-IT.md).

$echo '<jsonrpc initialize>' | npx -y @browserbasehq/mcprecorded session — replayed, not live
recorded 2026-09-05 · exit 0 · captured verbatim by our probe harness, secrets redacted

Verified integrations

Connections to other tracked products — hover a chip for the verbatim evidence quote behind it.

Browserbase logoBrowserbaseWeb Scraping APIsClaude Code logoClaude CodeAI Coding AgentsSmithery logoSmitheryMCP Infrastructure & Registries

By theme — the product's score on each story themeBy theme

Action primitives — stories about action primitives in this arenaAction primitivesevidence →

Stories about action primitives in this arena

57.5/100

Agenticness — how well agents can access and operate the productAgenticnessevidence →

How well agents can access and operate the product

43.6/100

Auth session persistence — stories about auth session persistence in this arenaAuth session persistenceevidence →

Stories about auth session persistence in this arena

44.6/100

Automation depth — how much of the product can run unattendedAutomation depthevidence →

How much of the product can run unattended

0.0/100

Deployment modes — stories about deployment modes in this arenaDeployment modesevidence →

Stories about deployment modes in this arena

70.0/100

Framework model support — stories about framework model support in this arenaFramework model supportevidence →

Stories about framework model support in this arena

12.0/100

Nl task execution — stories about nl task execution in this arenaNl task executionevidence →

Stories about nl task execution in this arena

21.4/100

Openness — open source, data portability, and self-hosting storiesOpennessevidence →

Open source, data portability, and self-hosting stories

13.5/100

Pricing limits — free-tier ceilings, usage caps, and rate limits before you have to payPricing limitsevidence →

Free-tier ceilings, usage caps, and rate limits before you have to pay

0.0/100

Privacy posture — data-handling and privacy storiesPrivacy postureevidence →

Data-handling and privacy stories

8.0/100

Replay debugging — stories about replay debugging in this arenaReplay debuggingevidence →

Stories about replay debugging in this arena

27.0/100

Scale parallelism — running many jobs at once — concurrency, fleets, queueingScale parallelismevidence →

Running many jobs at once — concurrency, fleets, queueing

0.0/100

Stealth captcha — stories about stealth captcha in this arenaStealth captchaevidence →

Stories about stealth captcha in this arena

19.2/100

Structured extraction — stories about structured extraction in this arenaStructured extractionevidence →

Stories about structured extraction in this arena

52.5/100

Story verdicts — every judged story with its evidenceStory verdicts

?

Sorted by importance (agentic first) (high → low) · 52/52 stories · click a row’s chevron for the rationale and evidence

Connect an agent via an official MCP server G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness3full8/10T

Delegate tasks to a built-in AI assistant inside the product G

Agentic features

ai-native userAgenticness — how well agents can access and operate the productAgenticness3full8/10X

Drive the product through a documented public API G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness3full8/10T

Plug MCP servers into this product so it can use their tools G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness3none0/10

Operate the product with natural-language commands G

Agentic features

ai-native userAgenticness — how well agents can access and operate the productAgenticness2full9/10X

Build against official SDKs G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2full8/10T

Point an agent at llms.txt or agent-oriented docs G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2full8/10T

Run the product headlessly / in CI for automation G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2full8/10T

Set up automations that run autonomously in the background G

Agentic features

ai-native userAgenticness — how well agents can access and operate the productAgenticness2partial5/10C

Download a machine-readable API spec (OpenAPI or equivalent) G

Api quality

ai-native userAgenticness — how well agents can access and operate the productAgenticness2none0/10

Explore an interactive API reference with runnable examples G

Api quality

ai-native userAgenticness — how well agents can access and operate the productAgenticness2none0/10

Issue scoped/least-privilege API credentials for an agent G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2none0/10

Rely on versioned APIs with a documented deprecation policy G

Api quality

ai-native userAgenticness — how well agents can access and operate the productAgenticness2none0/10

Use an official CLI G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2none0/10

Get AI-generated insights and suggestions from my data inside the product G

Agentic features

ai-native userAgenticness — how well agents can access and operate the productAgenticness2n/auntestednone yet

Subscribe to events via webhooks G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2n/auntestednone yet

Test against a sandbox environment without touching production data G

Api quality

ai-native userAgenticness — how well agents can access and operate the productAgenticness1noneuntestednone yet

Drive the page through DOM-understanding action primitives (act/click/type on described elements) that survive selector and layout changes C

Dom

developerAction primitives — stories about action primitives in this arenaAction primitives3full8/10X

Persist logged-in browser state in reusable profiles so agents skip the login wall on every subsequent run C

Profiles

developerAuth session persistence — stories about auth session persistence in this arenaAuth session persistence3full8/10C

Extract typed, schema-validated data (Zod/Pydantic-style) from pages the agent visits, not just raw text C

Extraction

developerStructured extraction — stories about structured extraction in this arenaStructured extraction3full7/10C

Self-host the core product G

ai-native userOpenness — open source, data portability, and self-hosting storiesOpenness3partial6/10T

Hand the product a natural-language goal and it completes a multi-step web task end to end — navigating, filling forms, and clicking through flows C

Tasks

developerNl task execution — stories about nl task execution in this arenaNl task execution3partial5/10X

Define rules that trigger actions automatically on events G

ai-native userAutomation depth — how much of the product can run unattendedAutomation depth3noneuntestednone yet

Export all of my data in open formats and leave G

ai-native userOpenness — open source, data portability, and self-hosting storiesOpenness3noneuntestednone yet

Prevent my data from being used to train AI models G

ai-native userPrivacy posture — data-handling and privacy storiesPrivacy posture3noneuntestednone yet

Cache resolved actions or generated code so repeat runs replay deterministically at lower cost and latency than re-prompting the LLM C

Caching

developerAction primitives — stories about action primitives in this arenaAction primitives2full7/10C

Run the agent against a local browser on my own machine for development, without any cloud account C

Local

developerDeployment modes — stories about deployment modes in this arenaDeployment modes2full7/10C

Choose where my data is stored (region/residency) G

ai-native userPrivacy posture — data-handling and privacy storiesPrivacy posture2partial6/10C

Connect my existing Playwright, Puppeteer, or CDP automation code to the product's browsers instead of rewriting it C

Compat

developerAuth session persistence — stories about auth session persistence in this arenaAuth session persistence2partial6/10X

Compose repeatable multi-step workflows with loops, conditionals, and parameters instead of one-shot prompts C

Workflows

automation-engineerNl task execution — stories about nl task execution in this arenaNl task execution2partial5/10C

Debug a failed agent run from recorded replays — video, screenshots, step-by-step action timelines C

Replay

automation-engineerReplay debugging — stories about replay debugging in this arenaReplay debugging2partial5/10C

Enable stealth fingerprinting and residential or geo-targeted proxies so legitimate automations aren't blocked as bots C

Stealth

automation-engineerStealth captcha — stories about stealth captcha in this arenaStealth captcha2partial5/10X

Plug the browser layer into agent frameworks (Claude Agent SDK, Vercel AI SDK, LangChain, CrewAI) through documented adapters C

Frameworks

developerFramework model support — stories about framework model support in this arenaFramework model support2partial4/10T

Watch a session live and take human control mid-run when the agent gets stuck C

Live

automation-engineerReplay debugging — stories about replay debugging in this arenaReplay debugging2partial4/10C

Rely on a documented captcha stance — automatic solving, human fallback, or explicit non-support — instead of silent task failures C

Captcha

automation-engineerStealth captcha — stories about stealth captcha in this arenaStealth captcha2partial3/10X

Bring my own LLM provider — the framework is model-agnostic rather than locked to one vendor's models C

Models

developerFramework model support — stories about framework model support in this arenaFramework model support2none0/10

Control data retention and deletion G

ai-native userPrivacy posture — data-handling and privacy storiesPrivacy posture2none0/10

Run a fleet of concurrent browser sessions with documented concurrency limits and programmatic session management C

Fleets

automation-engineerScale parallelism — running many jobs at once — concurrency, fleets, queueingScale parallelism2none0/10

Store credentials in a vault and have the agent complete logins including TOTP/2FA challenges without exposing secrets to the model G

Credentials

automation-engineerAuth session persistence — stories about auth session persistence in this arenaAuth session persistence2none0/10

Submit a browser task over a hosted HTTP API and receive the result by polling or webhook, without managing any browser myself C

Tasks

ai agentNl task execution — stories about nl task execution in this arenaNl task execution2none0/10

Switch to a vision or computer-use action mode that operates on screenshots for canvases and UIs the DOM path can't handle C

Vision

developerAction primitives — stories about action primitives in this arenaAction primitives2none0/10

Do everything through the API that I can do in the UI G

ai-native userOpenness — open source, data portability, and self-hosting storiesOpenness2n/auntestednone yet

Opt out of telemetry and usage tracking G

ai-native userPrivacy posture — data-handling and privacy storiesPrivacy posture2noneuntestednone yet

Perform bulk operations across many items at once G

ai-native userAutomation depth — how much of the product can run unattendedAutomation depth2noneuntestednone yet

Read the product's source under an open license G

ai-native userOpenness — open source, data portability, and self-hosting storiesOpenness2noneuntestednone yet

Schedule recurring jobs or workflows G

ai-native userAutomation depth — how much of the product can run unattendedAutomation depth2n/auntestednone yet

See transparent per-task or per-browser-hour pricing and documented rate/concurrency limits before committing G

Pricing

developerPricing limits — free-tier ceilings, usage caps, and rate limits before you have to payPricing limits2noneuntestednone yet

Preview candidate actions on the current page (observe/plan) before committing the agent to act C

Observe

developerAction primitives — stories about action primitives in this arenaAction primitives1full8/10T

Get webhook notifications when tasks and sessions finish instead of polling for status C

Lifecycle

developerScale parallelism — running many jobs at once — concurrency, fleets, queueingScale parallelism1noneuntestednone yet

My agent can download files from and upload files to the sites it operates, with the artifacts retrievable afterwards C

Files

developerStructured extraction — stories about structured extraction in this arenaStructured extraction1noneuntestednone yet

Point to the vendor's published acceptable-use and anti-abuse posture governing what its stealth and automation features may be used for C

Posture

automation-engineerStealth captcha — stories about stealth captcha in this arenaStealth captcha1noneuntestednone yet

Version, review, and roll back my automations G

ai-native userAutomation depth — how much of the product can run unattendedAutomation depth1n/auntestednone yet

Opportunities — the stories that would move this product's scores, from its own judged verdictsOpportunitiestop 8 of 34 stories with headroom

What would move Stagehand’s scores — derived from its own judged verdicts, biggest headroom first. Each line quotes what the judge found missing; shipping it (or evidencing it publicly) is the fix.

  1. Agenticness — how well agents can access and operate the productPlug MCP servers into this product so it can use their tools

    nonemoves agent-readyimpact 45

    All evidence shows Stagehand exposing its own browser-automation tools via MCP (server role) to other agents like Claude Code, not Stagehand acting as an MCP client that consumes external MCP servers' tools.

  2. Automation depth — how much of the product can run unattendedDefine rules that trigger actions automatically on events

    nonemoves PA Scoreimpact 30

    The evidence describes Stagehand's act/observe/extract primitives for executing AI-driven browser actions, caching, and self-healing selectors, but nothing about defining persistent rules that automatically trigger on events (e.g., webhooks, schedules, DOM-change listeners) outside of an explicit script invocation.

  3. Openness — open source, data portability, and self-hosting storiesExport all of my data in open formats and leave

    nonemoves PA Scoreimpact 30

    The axis applies to this product kind (peer products hold positive or none verdicts on this story), so lack of evidence for an applicable capability is "none", never "na".

  4. Privacy posture — data-handling and privacy storiesPrevent my data from being used to train AI models

    nonemoves PA Scoreimpact 30

    The axis applies to this product kind (peer products hold positive or none verdicts on this story), so lack of evidence for an applicable capability is "none", never "na".

  5. Agenticness — how well agents can access and operate the productUse an official CLI

    nonemoves agent-readyimpact 30

    Stagehand is distributed as an npm SDK/library plus an MCP server; the evidence pack shows npm install and MCP server invocation via npx, but no dedicated official CLI tool for direct AI-native command-line interaction is documented anywhere.

  6. Agenticness — how well agents can access and operate the productIssue scoped/least-privilege API credentials for an agent

    nonemoves agent-readyimpact 30

    Missing: any mention of scoped API key issuance, permission scoping, or least-privilege credential management for agents.

  7. Agenticness — how well agents can access and operate the productExplore an interactive API reference with runnable examples

    nonemoves API qualityimpact 30

    The evidence pack shows standard prose documentation pages (docs.stagehand.dev) and confirms no OpenAPI/swagger spec exists (404s on all candidate paths), with no mention anywhere of an interactive, runnable-example API reference (e.g., live code sandbox or Swagger-style explorer).

  8. Agenticness — how well agents can access and operate the productDownload a machine-readable API spec (OpenAPI or equivalent)

    nonemoves API qualityimpact 30

    Direct probes for OpenAPI/swagger specs at all standard paths returned 404, and no documentation mentions a downloadable machine-readable API spec; only an llms.txt exists which is not an API spec.

Showing the top 8 of 34 — every none/partial verdict in the story verdicts table is headroom.

Think a verdict is wrong? Every verdicts-table row has a Flag link — see the methodology.

Coverage map — which docs area, API section, or community source covers which judged storiesCoverage map5 surfaces · 24 covered stories

Where the cited evidence behind each covered verdict came from — the same citations the verdicts table shows, no extra judging.

V4 docs22 stories

Hacker News11 stories

docs.stagehand.dev11 stories

llms.txt3 stories

OpenAPI spec1 story

Probe proofs — replayable recordings from the probe harnessProbe proofs

Replayable recordings from our probe harness — see the Prove-It protocol to submit one.

$echo '<jsonrpc initialize>' | npx -y @browserbasehq/mcpreproduced
$ echo '<jsonrpc initialize>' | npx -y @browserbasehq/mcp
\|/Warning: BROWSERBASE_API_[redacted] environment variable not set. Using dummy value.
Warning: BROWSERBASE_PROJECT_ID environment variable not set. Using dummy value.
Warning: MODEL_API_[redacted] environment variable not set. Using dummy value.
{"result":{"protocolVersion":"2025-06-18","capabilities":{"resources":{"subscribe":true,"listChanged":true},"tools":{"listChanged":true}},"serverInfo":{"name":"Browserbase MCP Server","version":"3.0.0","description":"Cloud browser automation server powered by Browserbase and Stagehand. Enables LLMs to navigate websites, interact with elements, extract data, and capture screenshots using natural language commands.","capabilities":{"resources":{"subscribe":true,"listChanged":true},"tools":{}}}},"jsonrpc":"2.0","id":1}
\
proves: Connect an agent via an official MCP serverproves: Drive the page through DOM-understanding action primitives (act/click/type on described elements) that survive selector and layout changesrecorded 2026-09-05
$mktemp -d && npm install @browserbasehq/stagehand && node -e "import('@browserbasehq/stagehand').then(m=>console.log('PA_PROBE_OK Stagehand export:', typeof m.Stagehand))"reproduced
$ mktemp -d && npm install @browserbasehq/stagehand && node -e "import('@browserbasehq/stagehand').then(m=>console.log('PA_PROBE_OK Stagehand export:', typeof m.Stagehand))"
\|/-
added 49 packages in 622ms
-PA_PROBE_OK Stagehand export: function
proves: Build against official SDKsrecorded 2026-09-05

Claims vs evidence — vendor claims reconciled against independent verdictsClaims vs evidence

5 of 12 testable claims verified · 0 contradicted → integrity 42/100

14 distinct capability claims found in Stagehand’s own claimed-docs/GitHub materials, reconciled against our judge’s independent verdicts.

5

Verified

7

Unverified

0

Contradicted

12

Undersold

Verified (8)
Unverified (8)
Undersold (12)
Claims outside our story set (1)

Real capability claims found in Stagehand’s own materials, but no story in this arena’s taxonomy covers them yet — that’s feedback on the taxonomy, not a mark against the product.

  • “WebMCP lets an agent discover and invoke a site's own tools directly instead of multi-step clicking”

    source ↗
Suggest a story for these →

Business model

open-sourceusage-based

MIT-licensed open-source framework (TypeScript and Python) that runs on any local Chrome for free; pairing it with Browserbase's managed cloud browsers is where vendor usage pricing applies.

pricing ↗

Score trend

How this product’s scores have moved as evidence and verdicts are re-derived — a point per change, not per day.

PA Scoretracked since Sep 5 '26 — no movement recorded yet
Agent-readytracked since Sep 5 '26 — no movement recorded yet

Try Experimental

Run it in the microterminal →

Recorded agent sessions — and a live MCP handshake where the vendor ships one.

Flag

⚑ Flag a verdict

Think a verdict is wrong? Opens a prefilled GitHub issue — or use the ⚑ next to any verdict above.

Badge

Embed this product's score badge →

Hotlinked SVG — always shows the live current score.

For agents

This page as markdown/llms.txt

Data

Evidence (JSON)Verdicts (JSON)

Agent surface uptime llms.txt 100% (30d, checked every 6h since Sep 8 '26)