Skip to content
ProductArena

Rank #2 of 7 in Browser Automation for Agents

Skyvern logo

Skyvern

Open SourceYC S23 Built-in AI assistant

Skyvern AI, Inc.

skyvern.com ↗Try it →
PA Score31/100AGENT-READY42/100BUILT-IN AI62/100API0/100
MCP✓CLI—API✓
★ 23k▲ 9k/yr★ +73pypi/wk +119
ArenasBrowser Automation for Agents#2/7

Access

Open app ↗API docs ↗MCP docs ↗

Install

pippip install skyvern

Compare head-to-head

Browser Use logovs Browser UseStagehand logovs StagehandHyperbrowser logovs HyperbrowserSteel logovs SteelNotte logovs NotteSmooth logovs Smooth

Alternatives to Skyvern →

Showcase

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

Try itExperimental

See what an agent can do with Skyvern 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).

$curl -si -X POST https://api.skyvern.com/mcp -H 'Content-Type: application/json' -d '<jsonrpc initialize>'recorded 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 AssistantsClaude Code logoClaude CodeAI Coding AgentsCodex logoCodexAI Coding AgentsCursor logoCursorAI Coding AgentsZapier logoZapierWorkflow Automation

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

25.4/100

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

How well agents can access and operate the product

37.8/100

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

Stories about auth session persistence in this arena

44.0/100

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

How much of the product can run unattended

6.7/100

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

Stories about deployment modes in this arena

36.0/100

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

Stories about framework model support in this arena

18.0/100

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

Stories about nl task execution in this arena

23.6/100

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

Open source, data portability, and self-hosting stories

39.0/100

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

20.0/100

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

Stories about replay debugging in this arena

80.0/100

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

32.0/100

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

Stories about structured extraction in this arena

60.0/100

Story verdicts — every judged story with its evidenceStory verdicts

What’s free: 2 free · 0 paid · 0 enterprise · 29 not stated in evidence

?

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 productAgenticness3full7/10C

Drive the product through a documented public API G

Agent access

ai-native userAgenticness — how well agents can access and operate the productAgenticness3full7/10T

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

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

Operate the product with natural-language commands G

Agentic features

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

Run the product headlessly / in CI for automation G

Agent access

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

Set up automations that run autonomously in the background G

Agentic features

ai-native userAgenticness — how well agents can access and operate the productAgenticness2partial7/10X

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 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 productAgenticness1noneuntestednone yet

Self-host the core product G

ai-native userOpenness — open source, data portability, and self-hosting storiesOpenness3fullfree8/10T

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

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 persistence3partial6/10C

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 primitives3disputed5/10D

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 execution3disputed5/10D

Prevent my data from being used to train AI models G

ai-native userPrivacy posture — data-handling and privacy storiesPrivacy posture3partial4/10C

Define rules that trigger actions automatically on events G

ai-native userAutomation depth — how much of the product can run unattendedAutomation depth3partial3/10C

Export all of my data in open formats and leave G

ai-native userOpenness — open source, data portability, and self-hosting storiesOpenness3partial3/10C

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 debugging2full8/10X

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

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 debugging2full8/10C

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 persistence2full7/10X

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 primitives2full7/10C

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 support2partial6/10C

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

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 modes2partial6/10C

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

ai-native userPrivacy posture — data-handling and privacy storiesPrivacy posture2partial5/10C

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 execution2partial5/10C

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 persistence2partial5/10C

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 execution2partial5/10T

Control data retention and deletion G

ai-native userPrivacy posture — data-handling and privacy storiesPrivacy posture2partial4/10X

Read the product's source under an open license G

ai-native userOpenness — open source, data portability, and self-hosting storiesOpenness2disputedfree4/10D

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 primitives2none0/10

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 captcha2none0/10

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

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

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 limits2none0/10

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

Schedule recurring jobs or workflows G

ai-native userAutomation depth — how much of the product can run unattendedAutomation depth2noneuntestednone 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 extraction1partial5/10C

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 primitives1partial3/10X

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

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 depth1noneuntestednone 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 Skyvern’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

    Evidence only shows Skyvern exposing an MCP *server* so external AI assistants (Claude, Cursor, etc.) can control Skyvern's browser — the reverse of the story, which asks whether Skyvern can consume external MCP servers' tools as a client.

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

    nonemoves agent-readyimpact 30

    Missing: any documented CLI command, npm/pip CLI package, or terminal-based interface.

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

    nonemoves agent-readyimpact 30

    Missing: any documentation of scoped API tokens, role-based access control, or least-privilege credential management for agents.

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

    nonemoves agent-readyimpact 30

    No evidence in the pack mentions webhooks or event subscriptions of any kind; Skyvern's documented integration surfaces are REST/SDK APIs, Zapier, and an MCP server, none of which constitute a webhook subscription mechanism.

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

    nonemoves API qualityimpact 30

    Evidence shows only static docs describing SDKs and REST usage, with no interactive API reference or runnable-example explorer; probes explicitly found no OpenAPI/Swagger spec at any candidate path (404s), indicating no interactive reference exists.

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

    nonemoves API qualityimpact 30

    Skyvern offers a REST API (skyvern-docs-1) but a direct probe for OpenAPI/swagger specs at standard paths returned 404 across all candidates, and no docs mention a downloadable machine-readable spec.

  7. Agenticness — how well agents can access and operate the productRely on versioned APIs with a documented deprecation policy

    nonemoves API qualityimpact 30

    Missing: versioned API endpoints (e.g., /v1/), a published deprecation/support policy, and changelog documentation.

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

    partialq3/10moves PA Scoreimpact 21

    Missing: documented native event triggers or webhook listeners, schedule-based triggers, and any conditional rule engine inside Skyvern's workflow builder.

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 map9 surfaces · 32 covered stories

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

docs31 stories

Hacker News10 stories

GitHub README6 stories

OpenAPI spec5 stories

Developers docs5 stories

Llms docs5 stories

llms.txt3 stories

Pricing docs2 stories

Integrations 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.

$curl -si -X POST https://api.skyvern.com/mcp -H 'Content-Type: application/json' -d '<jsonrpc initialize>'reproduced
$ curl -si -X POST https://api.skyvern.com/mcp -H 'Content-Type: application/json' -d '<jsonrpc initialize>'
HTTP/2 401

date: Sat, 05 Sep 2026 01:14:54 GMT

content-type: application/json

content-length: 291

set-cookie: AWSALB=nTUpYIpFlHgwlQJKvT98WAFsTxb/WDSd4RuXF5Sk3Z0B0LbVi9Pw+v57Y2tQ77ZfGfZixha4PsvbWQrByBYZ8H5Er+nGW/gmHUCgFXlse0P5FOq2AQynwWZeJMJf; Expires=Sat, 12 Sep 2026 01:14:54 GMT; Path=/

set-cookie: AWSALBCORS=nTUpYIpFlHgwlQJKvT98WAFsTxb/WDSd4RuXF5Sk3Z0B0LbVi9Pw+v57Y2tQ77ZfGfZixha4PsvbWQrByBYZ8H5Er+nGW/gmHUCgFXlse0P5FOq2AQynwWZeJMJf; Expires=Sat, 12 Sep 2026 01:14:54 GMT; Path=/; SameSite=None; Secure

server: uvicorn

www-authenticate: Bearer realm="mcp", resource_metadata="https://api.skyvern.com/.well-known/oauth-protected-resource/mcp"

access-control-expose-headers: WWW-Authenticate

ratelimit-policy: "submit-run";q=50;w=60

x-frame-options: DENY

content-security-policy: frame-ancestors 'none'

{"error":{"code":"UNAUTHORIZED","message":"Missing credentials. Use an API [redacted] from https://app.skyvern.com Settings (Claude Desktop: Settings -> Extensions -> Skyvern -> Configure) or connect with an OAuth-capable client. Docs: https://www.skyvern.com/docs/developers/getting-started/mcp"}}
proves: Connect an agent via an official MCP serverproves: Submit a browser task over a hosted HTTP API and receive the result by polling or webhook, without managing any browser myselfrecorded 2026-09-05
$mktemp -d && uv venv && uv pip install skyvern && skyvern --helpreproduced
$ mktemp -d && uv venv && uv pip install skyvern && skyvern --help
PA_PROBE_OK skyvern 1.0.48

 Usage: skyvern [OPTIONS] COMMAND [ARGS]...

 Skyvern CLI Manage and run your local Skyvern environment.

╭─ Options ────────────────────────────────────────────────────────────────────╮
│ --install-completion          Install completion for the current shell.      │
│ --show-completion             Show completion for the current shell, to copy │
proves: Build against official SDKsproves: Use an official CLIproves: 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

6 of 14 testable claims verified · 1 contradicted → integrity 29/100

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

6

Verified

7

Unverified

1

Contradicted

16

Undersold

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

Real capability claims found in Skyvern’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.

  • “Cloud UI dashboard lets you build and run automations visually with drag-and-drop blocks, no code required”

    source ↗

  • “Offers a Zapier integration to connect automations with other apps”

    source ↗
Suggest a story for these →

Business model

open-sourcefree-tierusage-basedenterprise-custom

AGPL-3.0 open-source core you can self-host; Skyvern Cloud is priced per task-step usage with a free starting credit and enterprise plans for managed scale.

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 Score32 (Sep 5 '26)31 (Sep 16 '26)
Agent-ready49 (Sep 5 '26)42 (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 MCP 100% · llms.txt 100% (30d, checked every 6h since Sep 8 '26)