Skip to content
ProductArena

Rank #6 of 7 in Browser Automation for Agents

Browser Use logo

Browser Use

Open SourceYC W25

Browser Use, Inc.

browser-use.com ↗Try it →
PA Score23/100AGENT-READY30/100BUILT-IN AI45/100API0/100
MCP!CLI—API~
★ 114.6k▲ 61.3k/yrnpm 70.5k/wkpypi 1.7M/wk★ +2.3knpm/wk -18.6kpypi/wk +70.8k
ArenasBrowser Automation for Agents#6/7

Access

Open app ↗API docs ↗MCP docs ↗

Install

pippip install browser-use
npmnpm install browser-use-sdk

Compare head-to-head

Stagehand logovs StagehandSkyvern logovs SkyvernHyperbrowser logovs HyperbrowserSteel logovs SteelNotte logovs NotteSmooth logovs Smooth

Alternatives to Browser Use →

Showcase

Browser Use homepage screenshot
homepage · captured Sep 2026 · view live ↗
Browser Use docs screenshot
docs · captured Sep 2026 · view live ↗

Try itExperimental

See what an agent can do with Browser Use 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>' | uvx --from 'browser-use[cli]' browser-use --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.

Claude logoClaudeAI AssistantsCursor logoCursorAI Coding AgentsGemini logoGeminiAI Assistants

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

13.5/100

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

How well agents can access and operate the product

26.2/100

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

Stories about auth session persistence in this arena

62.9/100

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

How much of the product can run unattended

4.5/100

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

Stories about deployment modes in this arena

80.0/100

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

Stories about framework model support in this arena

40.0/100

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

Stories about nl task execution in this arena

57.1/100

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

Open source, data portability, and self-hosting stories

34.2/100

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

24.0/100

Privacy posture — data-handling and privacy storiesPrivacy postureevidence →

Data-handling and privacy stories

0.0/100

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

Stories about replay debugging in this arena

30.0/100

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

Running many jobs at once — concurrency, fleets, queueing

16.0/100

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

Stories about stealth captcha in this arena

60.0/100

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

Stories about structured extraction in this arena

18.0/100

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

Drive the product through a documented public API G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness3partial7/10T

Connect an agent via an official MCP server G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness3disputed5/10D

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 productAgenticness3n/a0/10

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 productAgenticness3n/a±untestednone yet

Operate the product with natural-language commands G

Agentic features

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

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

Build against official SDKs G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2full7/10T

Run the product headlessly / in CI for automation G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2partial±6/10C

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

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 productAgenticness2partial±4/10C

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

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

Subscribe to events via webhooks G

Agent access

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 productAgenticness2noneuntestednone yet

Use an official CLI G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness2noneuntestednone yet

Test against a sandbox environment without touching production data G

Api quality

ai-native userAgenticness — how well agents can access and operate the productAgenticness1none±0/10

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 execution3full8/10X

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 persistence3full8/10X

Self-host the core product G

ai-native userOpenness — open source, data portability, and self-hosting storiesOpenness3full7/10T

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 primitives3partial6/10X

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 extraction3partial4/10C

Define rules that trigger actions automatically on events G

ai-native userAutomation depth — how much of the product can run unattendedAutomation depth3none0/10

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

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 support2full8/10X

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 captcha2full8/10C

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 modes2full8/10X

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 execution2full8/10T

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 persistence2full7/10X

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 captcha2full7/10C

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

ai-native userOpenness — open source, data portability, and self-hosting storiesOpenness2partial6/10T

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 debugging2partial6/10C

Read the product's source under an open license G

ai-native userOpenness — open source, data portability, and self-hosting storiesOpenness2partial5/10T

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 persistence2partial5/10C

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 debugging2partial4/10C

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 parallelism2partial4/10C

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 limits2partial4/10C

Perform bulk operations across many items at once G

ai-native userAutomation depth — how much of the product can run unattendedAutomation depth2partial3/10C

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 execution2none0/10

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 support2none0/10

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 primitives2noneuntestednone yet

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

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

Control data retention and deletion G

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

Opt out of telemetry and usage tracking G

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

Schedule recurring jobs or workflows G

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

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 primitives2noneuntestednone yet

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 parallelism1none0/10

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 extraction1none0/10

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 primitives1none0/10

Version, review, and roll back my automations G

ai-native userAutomation depth — how much of the product can run unattendedAutomation depth1none0/10

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

Opportunities — the stories that would move this product's scores, from its own judged verdictsOpportunitiestop 8 of 37 stories with headroom

What would move Browser Use’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. Automation depth — how much of the product can run unattendedDefine rules that trigger actions automatically on events

    nonemoves PA Scoreimpact 30

    Browser Use's evidence covers on-demand task runs, sessions, observability polling, CAPTCHA/stealth, and MCP integration, but nothing describes user-defined rules or triggers that fire actions automatically on external events (e.g., webhooks, schedules, conditional triggers).

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

    nonemoves PA Scoreimpact 30

    The evidence pack describes agent runs, sessions, CAPTCHA handling, and pricing, but nothing documents an account/data export feature (e.g., downloading all run history, sessions, or stored data in an open format) that would let a user leave the platform with their data intact; the open-source library allows self-hosting but that's a separate capability from exporting existing cloud account data.

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

    nonemoves PA Scoreimpact 30

    No evidence in the pack addresses data usage for AI model training, opt-out policies, or privacy/data-retention commitments for Browser Use Cloud or the open-source library.

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

    nonemoves agent-readyimpact 30

    The evidence pack documents a Python SDK, cloud API, MCP server, and web dashboard, but never mentions an official standalone CLI tool for Browser Use.

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

    nonemoves agent-readyimpact 30

    No evidence of scoped or least-privilege API key/credential issuance (e.g., role-based tokens, permission scopes) for agents; docs mention API keys implicitly via client usage but no mention of scoping, restricted permissions, or credential management features.

  6. Agenticness — how well agents can access and operate the productSubscribe to events via webhooks

    nonemoves agent-readyimpact 30

    The docs describe an event system based on polling `runs.events()` with a cursor, not webhook subscriptions; no evidence anywhere in the pack mentions webhooks, callback URLs, or push notifications.

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

    nonemoves API qualityimpact 30

    Docs show static code snippets (e.g., client.runs.create examples) but no evidence of an interactive, runnable API console/reference; explicit probes for OpenAPI/Swagger specs at standard paths all returned 404, indicating no interactive API explorer exists.

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

    nonemoves API qualityimpact 30

    A direct probe for OpenAPI/swagger spec files returned 404 on all candidate paths, and no documentation references a downloadable machine-readable API spec despite having a REST/cloud API.

Showing the top 8 of 37 — 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 map7 surfaces · 27 covered stories

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

Cloud docs18 stories

docs.browser-use.com16 stories

GitHub README13 stories

Hacker News9 stories

llms.txt4 stories

OpenAPI spec4 stories

Pricing docs1 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>' | uvx --from 'browser-use[cli]' browser-use --mcpreproduced
$ echo '<jsonrpc initialize>' | uvx --from 'browser-use[cli]' browser-use --mcp
⠋ Resolving dependencies...                                                     
⠙ Resolving dependencies...                                                     
⠋ Resolving dependencies...                                                     
⠙ Resolving dependencies...                                                     
⠙ browser-use==0.13.10                                                          
⠙ browser-use==0.13.10                                                          
⠙ aiohttp==3.14.3                                                               
⠙ anthropic==0.76.0                                                             
⠙ anyio==4.12.1                                                                 
⠙ browser-harness==0.1.13                                                       
⠙ browser-use-sdk==3.4.2                                                        
⠙ bubus==1.5.6                                                                  
⠙ cdp-use==1.4.5                                                                
⠙ click==8.3.3                                                                  
⠙ cloudpickle==3.1.2                                                            
⠙ google-api-core==2.29.0                                                       
⠙ google-api-python-client==2.188.0                                             
⠙ google-auth-oauthlib==1.2.4                                                   
⠙ google-auth==2.48.0                                                           
⠙ google-genai==1.65.0                                                          
⠙ google-auth==2.48.0                                                           
⠙ groq==1.0.0                                                                   
⠙ httpx==0.28.1                                                                 
⠙ websockets==15.0.1                                                            
{"jsonrpc":"2.0","id":1,"result":{"capabilities":{"experimental":{},"prompts":{"listChanged":false},"resources":{"listChanged":false,"subscribe":false},"tools":{"listChanged":false}},"protocolVersion":"2025-06-18","serverInfo":{"name":"browser-use","version":"0.13.10"}}}
proves: Connect an agent via an official MCP serverproves: Hand the product a natural-language goal and it completes a multi-step web task end to end — navigating, filling forms, and clicking through flowsrecorded 2026-09-05
$mktemp -d && uv venv && uv pip install browser-use && python -c "import browser_use; print('PA_PROBE_OK browser-use', version('browser-use'))"reproduced
$ mktemp -d && uv venv && uv pip install browser-use && python -c "import browser_use; print('PA_PROBE_OK browser-use', version('browser-use'))"
PA_PROBE_OK browser-use 0.13.10
proves: Build against official SDKsproves: Run the agent against a local browser on my own machine for development, without any cloud accountrecorded 2026-09-05

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

5 of 11 testable claims verified · 1 contradicted → integrity 27/100

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

5

Verified

5

Unverified

1

Contradicted

16

Undersold

Verified (6)
Unverified (7)
Contradicted (1)
Undersold (16)
Claims outside our story set (2)

Real capability claims found in Browser Use’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.

  • “A session preserves conversation state and its live browser across multiple runs”

    source ↗

  • “New eligible signups get a one-time $15 usage credit with no card required”

    source ↗
Suggest a story for these →

Business model

open-sourcefree-tierusage-based

MIT-licensed open-source Python library; Browser Use Cloud sells hosted agents and browsers on credit-based usage pricing (per-step/browser-time plus model tokens) with a free starting balance.

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 Score39 (Sep 5 '26)23 (Sep 16 '26)
Agent-ready50 (Sep 5 '26)30 (Sep 16 '26)

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)