Skip to content
ProductArena

How Hyperbrowser’s scores are calculated

The full audit trail, recomputed from the verdict data at build time through the same code that produced the leaderboard: verdict × quality × story weight per cell, cells sum to dimension scores, dimensions blend into the PA Score. Every number on the product page is reproducible from this page alone; for why the formula looks like this, see the methodology.

verdict factors: full ×1.0 · partial ×0.6 · disputed ×0.3 · none ×0.0 · n/a excluded from both sides · cell points = weight × quality × factor · cell max = weight × 10

PA Score30/100

Agent-ready 48.6 × 0.30 = 14.58

API quality 10.3 × 0.20 = 2.06

Openness 14.0 × 0.20 = 2.80

Built-in AI 59.7 × 0.15 = 8.96

Automation 9.0 × 0.15 = 1.35

(14.58 + 2.06 + 2.80 + 8.96 + 1.35) ÷ (0.30 + 0.20 + 0.20 + 0.15 + 0.15) = 29.75 ÷ 1.00 = 29.7

Scores are stored to 1 decimal; the product page’s pills round to whole numbers for display. Each dimension below shows the stories, verdicts, and cited evidence behind its number.

Agent-ready48.6/100×0.30 of the PA blend

Outside-in: can YOUR agent reach and drive this product — API, MCP, CLI, headless runs, agent docs.

Point an agent at llms.txt or agent-oriented docsweight 2

2 (weight) × 8 (quality) × 1.0 (full) = 16.0 of 20 max

  • [probe] https://hyperbrowser.ai/llms.txt“PROBE llms.txt: HTTP 200 at https://hyperbrowser.ai/llms.txt # Hyperbrowser > Hyperbrowser provides fast cloud browsers for AI agents and automation — managed browser sessions, web”
  • [probe] https://hyperbrowser.ai/docs.md“PROBE docs-md: HTTP 404 at https://hyperbrowser.ai/docs.md”
  • [probe] https://hyperbrowser.ai/openapi.json“PROBE openapi: all candidate paths 404 (https://hyperbrowser.ai/openapi.json, https://hyperbrowser.ai/swagger.json, https://hyperbrowser.ai/api/openapi.json, https://hyperbrowser.ai/.well-known/openapi.json)”
  • [claimed-docs] https://hyperbrowser.ai/docs/integrations/model-context-protocol“The Hyperbrowser MCP server provides a standardized interface for AI models to access powerful web automation capabilities like scraping, structured extraction, and crawling.”
  • [probe] https://hyperbrowser.ai/docs/integrations/model-context-protocol“official MCP server documented at https://hyperbrowser.ai/docs/integrations/model-context-protocol”

Run the product headlessly / in CI for automationweight 2

2 (weight) × 8 (quality) × 1.0 (full) = 16.0 of 20 max

  • [claimed-docs] https://hyperbrowser.ai/docs/sessions/create.md“Sessions are isolated browser instances running in the cloud that you can control programmatically. Each session gives you a WebSocket endpoint to connect with Playwright, Puppeteer, or any CDP-compatible tool.”
  • [claimed-docs] https://hyperbrowser.ai/docs/introduction.md“Control Chrome browsers in the cloud using Puppeteer, Playwright, or our SDKs—no infrastructure management required.”
  • [claimed-docs] https://hyperbrowser.ai/docs/sdks/introduction.md“Official SDKs for integrating Hyperbrowser into your applications”
  • [claimed-docs] https://hyperbrowser.ai/docs/sandboxes/install.md“Set up the Hyperbrowser CLI (`hx`) and/or the SDKs to start working with sandboxes.”
  • [claimed-docs] https://hyperbrowser.ai/docs“Connect your existing automation scripts to cloud browsers”
  • [claimed-docs] https://hyperbrowser.ai/docs/web-scraping/scrape.md“The Scrape API allows you to get the data you want from web pages with a single call. You can scrape page content and capture its data in various formats like markdown or html.”
  • [claimed-docs] https://hyperbrowser.ai/docs/web-scraping/crawl.md“The Crawl API allows you to crawl websites and get data from multiple pages in a single request. Starting from a URL, it can navigate through the site and extract content from linked pages.”

Plug MCP servers into this product so it can use their toolsweight 3

3 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 30 max

  • [claimed-docs] https://hyperbrowser.ai/docs/integrations/model-context-protocol“The Hyperbrowser MCP server provides a standardized interface for AI models to access powerful web automation capabilities like scraping, structured extraction, and crawling.”
  • [github] https://github.com/hyperbrowserai/mcp“`scrape_webpage` - Extract formatted (markdown, screenshot etc) content from any webpage”
  • [probe] https://hyperbrowser.ai/docs/integrations/model-context-protocol“official MCP server documented at https://hyperbrowser.ai/docs/integrations/model-context-protocol”

Connect an agent via an official MCP serverweight 3

3 (weight) × 8 (quality) × 1.0 (full) = 24.0 of 30 max

  • [claimed-docs] https://hyperbrowser.ai/docs/integrations/model-context-protocol“The Hyperbrowser MCP server provides a standardized interface for AI models to access powerful web automation capabilities like scraping, structured extraction, and crawling.”
  • [github] https://github.com/hyperbrowserai/mcp“`scrape_webpage` - Extract formatted (markdown, screenshot etc) content from any webpage”
  • [probe] https://hyperbrowser.ai/docs/integrations/model-context-protocol“official MCP server documented at https://hyperbrowser.ai/docs/integrations/model-context-protocol”

Use an official CLIweight 2

2 (weight) × 5 (quality) × 0.6 (partial) = 6.0 of 20 max

  • [claimed-docs] https://hyperbrowser.ai/docs/sandboxes/install.md“Set up the Hyperbrowser CLI (`hx`) and/or the SDKs to start working with sandboxes.”

Drive the product through a documented public APIweight 3

3 (weight) × 8 (quality) × 1.0 (full) = 24.0 of 30 max

  • [claimed-docs] https://hyperbrowser.ai/docs/web-scraping/scrape.md“The Scrape API allows you to get the data you want from web pages with a single call. You can scrape page content and capture its data in various formats like markdown or html.”
  • [claimed-docs] https://hyperbrowser.ai/docs/web-scraping/crawl.md“The Crawl API allows you to crawl websites and get data from multiple pages in a single request. Starting from a URL, it can navigate through the site and extract content from linked pages.”
  • [claimed-docs] https://hyperbrowser.ai/docs/web-scraping/extract.md“The Extract API allows you to extract structured data from web pages using AI. You can define a schema and prompt, and Hyperbrowser will extract the data matching your requirements.”
  • [claimed-docs] https://hyperbrowser.ai/docs/sdks/introduction.md“Official SDKs for integrating Hyperbrowser into your applications”
  • [claimed-docs] https://hyperbrowser.ai/docs/introduction.md“Control Chrome browsers in the cloud using Puppeteer, Playwright, or our SDKs—no infrastructure management required.”
  • [claimed-docs] https://hyperbrowser.ai/docs/sessions/create.md“Sessions are isolated browser instances running in the cloud that you can control programmatically. Each session gives you a WebSocket endpoint to connect with Playwright, Puppeteer, or any CDP-compatible tool.”
  • [probe] https://hyperbrowser.ai/llms.txt“PROBE llms.txt: HTTP 200 at https://hyperbrowser.ai/llms.txt # Hyperbrowser > Hyperbrowser provides fast cloud browsers for AI agents and automation — managed browser sessions, web”
  • [probe] https://hyperbrowser.ai/openapi.json“PROBE openapi: all candidate paths 404 (https://hyperbrowser.ai/openapi.json, https://hyperbrowser.ai/swagger.json, https://hyperbrowser.ai/api/openapi.json, https://hyperbrowser.ai/.well-known/openapi.json)”
  • [community] https://news.ycombinator.com/item?id=42381712“one quick nit on your docs: https://docs.hyperbrowser.ai/guides/scrape-site ... should be [corrected code with 'let' instead of 'const']”

Issue scoped/least-privilege API credentials for an agentweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

  • [claimed-docs] https://hyperbrowser.ai/docs/pricing.md“Hyperbrowser tracks your usage via `credits` which can be acquired through a subscription or through a direct purchase.”

Build against official SDKsweight 2

2 (weight) × 8 (quality) × 1.0 (full) = 16.0 of 20 max

  • [claimed-docs] https://hyperbrowser.ai/docs/sdks/introduction.md“Official SDKs for integrating Hyperbrowser into your applications”
  • [claimed-docs] https://hyperbrowser.ai/docs/introduction.md“Control Chrome browsers in the cloud using Puppeteer, Playwright, or our SDKs—no infrastructure management required.”
  • [claimed-docs] https://hyperbrowser.ai/docs“Connect your existing automation scripts to cloud browsers”
  • [claimed-docs] https://hyperbrowser.ai/docs/sandboxes/install.md“Set up the Hyperbrowser CLI (`hx`) and/or the SDKs to start working with sandboxes.”

Subscribe to events via webhooksweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Agent-ready = 102.0 ÷ 210 × 100 = 48.6

API quality10.3/100×0.20 of the PA blend

The programmable surface once an agent is there — machine-readable spec, interactive docs, sandbox, versioning discipline.

Explore an interactive API reference with runnable examplesweight 2

2 (weight) × 3 (quality) × 0.6 (partial) = 3.6 of 20 max

  • [claimed-docs] https://hyperbrowser.ai/docs/api-reference/fetch-a-web-page.md“Fetches a web page and returns the content in various formats (HTML, Markdown, JSON, screenshot, etc.)”
  • [claimed-docs] https://hyperbrowser.ai/docs/hyperagent/quickstart“await page.ai("search for flights from Miami to LAX, select the cheapest option");”
  • [claimed-docs] https://hyperbrowser.ai/docs/hyperagent/extract“The `page.extract()` method pulls structured data from web pages. Define what you want using natural language and optionally enforce a schema with Zod for type-safe results.”
  • [probe] https://hyperbrowser.ai/openapi.json“PROBE openapi: all candidate paths 404 (https://hyperbrowser.ai/openapi.json, https://hyperbrowser.ai/swagger.json, https://hyperbrowser.ai/api/openapi.json, https://hyperbrowser.ai/.well-known/openapi.json)”

Download a machine-readable API spec (OpenAPI or equivalent)weight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

  • [probe] https://hyperbrowser.ai/openapi.json“PROBE openapi: all candidate paths 404 (https://hyperbrowser.ai/openapi.json, https://hyperbrowser.ai/swagger.json, https://hyperbrowser.ai/api/openapi.json, https://hyperbrowser.ai/.well-known/openapi.json)”
  • [probe] https://hyperbrowser.ai/docs.md“PROBE docs-md: HTTP 404 at https://hyperbrowser.ai/docs.md”
  • [claimed-docs] https://hyperbrowser.ai/docs/api-reference/fetch-a-web-page.md“Fetches a web page and returns the content in various formats (HTML, Markdown, JSON, screenshot, etc.)”

Test against a sandbox environment without touching production dataweight 1

1 (weight) × 6 (quality) × 0.6 (partial) = 3.6 of 10 max

  • [claimed-docs] https://hyperbrowser.ai/docs/sandboxes/introduction.md“Hyperbrowser Sandboxes are the fastest sandboxes with less than 50ms startup time.”
  • [claimed-docs] https://hyperbrowser.ai/docs/sandboxes/introduction.md“const result = await sandbox.exec("node -e 'console.log(\"hello world\")'");”
  • [claimed-docs] https://hyperbrowser.ai/docs/sandboxes/install.md“Set up the Hyperbrowser CLI (`hx`) and/or the SDKs to start working with sandboxes.”
  • [claimed-docs] https://hyperbrowser.ai/docs/sessions/create.md“Sessions are isolated browser instances running in the cloud that you can control programmatically. Each session gives you a WebSocket endpoint to connect with Playwright, Puppeteer, or any CDP-compatible tool.”

Rely on versioned APIs with a documented deprecation policyweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

  • [probe] https://hyperbrowser.ai/openapi.json“PROBE openapi: all candidate paths 404 (https://hyperbrowser.ai/openapi.json, https://hyperbrowser.ai/swagger.json, https://hyperbrowser.ai/api/openapi.json, https://hyperbrowser.ai/.well-known/openapi.json)”
  • [probe] https://hyperbrowser.ai/docs.md“PROBE docs-md: HTTP 404 at https://hyperbrowser.ai/docs.md”

API quality = 7.2 ÷ 70 × 100 = 10.3

Openness14.0/100×0.20 of the PA blend

Can you leave, inspect, or self-host — data export, open source, portability.

Do everything through the API that I can do in the UIweight 2

2 (weight) × 7 (quality) × 1.0 (full) = 14.0 of 20 max

  • [claimed-docs] https://hyperbrowser.ai/docs/agents/overview“Hyperbrowser lets you run powerful, AI-driven browser agents in managed cloud sessions... you can start tasks with a single API call and watch them execute live.”
  • [claimed-docs] https://hyperbrowser.ai/docs/sessions/create.md“Sessions are isolated browser instances running in the cloud that you can control programmatically. Each session gives you a WebSocket endpoint to connect with Playwright, Puppeteer, or any CDP-compatible tool.”
  • [claimed-docs] https://hyperbrowser.ai/docs/web-scraping/scrape.md“The Scrape API allows you to get the data you want from web pages with a single call. You can scrape page content and capture its data in various formats like markdown or html.”
  • [claimed-docs] https://hyperbrowser.ai/docs/web-scraping/crawl.md“The Crawl API allows you to crawl websites and get data from multiple pages in a single request. Starting from a URL, it can navigate through the site and extract content from linked pages.”
  • [claimed-docs] https://hyperbrowser.ai/docs/web-scraping/extract.md“The Extract API allows you to extract structured data from web pages using AI. You can define a schema and prompt, and Hyperbrowser will extract the data matching your requirements.”
  • [claimed-docs] https://hyperbrowser.ai/docs/sandboxes/introduction.md“Hyperbrowser Sandboxes are the fastest sandboxes with less than 50ms startup time.”
  • [claimed-docs] https://hyperbrowser.ai/docs/sandboxes/install.md“Set up the Hyperbrowser CLI (`hx`) and/or the SDKs to start working with sandboxes.”
  • [probe] https://hyperbrowser.ai/openapi.json“PROBE openapi: all candidate paths 404 (https://hyperbrowser.ai/openapi.json, https://hyperbrowser.ai/swagger.json, https://hyperbrowser.ai/api/openapi.json, https://hyperbrowser.ai/.well-known/openapi.json)”

Export all of my data in open formats and leaveweight 3

3 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 30 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Read the product's source under an open licenseweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

  • [claimed-docs] https://hyperbrowser.ai/docs/agents/hyperagent“HyperAgent is our open-source tool that supercharges Playwright with AI.”
  • [claimed-docs] https://hyperbrowser.ai/docs/hyperagent/overview.md“HyperAgent is an open-source browser automation framework that extends Playwright with AI capabilities. Write natural language commands instead of complex selectors”
  • [claimed-docs] https://hyperbrowser.ai/docs/pricing.md“Hyperbrowser tracks your usage via `credits` which can be acquired through a subscription or through a direct purchase.”

Self-host the core productweight 3

3 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 30 max

  • [claimed-docs] https://hyperbrowser.ai/docs/introduction.md“Control Chrome browsers in the cloud using Puppeteer, Playwright, or our SDKs—no infrastructure management required.”
  • [claimed-docs] https://hyperbrowser.ai/docs/sandboxes/introduction.md“Hyperbrowser Sandboxes are the fastest sandboxes with less than 50ms startup time.”
  • [claimed-docs] https://hyperbrowser.ai/docs/agents/hyperagent“HyperAgent is our open-source tool that supercharges Playwright with AI.”

Openness = 14.0 ÷ 100 × 100 = 14.0

Built-in AI59.7/100×0.15 of the PA blend

Inside-out: how agentic the product itself is for its users — built-in assistants, autonomous features.

Get AI-generated insights and suggestions from my data inside the productweight 2

n/a — not applicable to this product: excluded from numerator and denominator

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Set up automations that run autonomously in the backgroundweight 2

2 (weight) × 4 (quality) × 0.6 (partial) = 4.8 of 20 max

  • [claimed-docs] https://hyperbrowser.ai/docs/agents/overview“Hyperbrowser lets you run powerful, AI-driven browser agents in managed cloud sessions... you can start tasks with a single API call and watch them execute live.”
  • [claimed-docs] https://hyperbrowser.ai/docs/agents/overview.md“Hyperbrowser lets you run powerful, AI-driven browser agents in managed cloud sessions. Whether you prefer open-source frameworks or cutting‑edge model-native agents, you can start tasks with a single API call and watch them execute live.”
  • [claimed-docs] https://hyperbrowser.ai/docs/introduction.md“Control Chrome browsers in the cloud using Puppeteer, Playwright, or our SDKs—no infrastructure management required.”
  • [claimed-docs] https://hyperbrowser.ai/docs“Connect your existing automation scripts to cloud browsers”

Delegate tasks to a built-in AI assistant inside the productweight 3

3 (weight) × 7 (quality) × 1.0 (full) = 21.0 of 30 max

  • [claimed-docs] https://hyperbrowser.ai/docs/agents/overview“Hyperbrowser lets you run powerful, AI-driven browser agents in managed cloud sessions... you can start tasks with a single API call and watch them execute live.”
  • [claimed-docs] https://hyperbrowser.ai/docs/hyperagent/quickstart“await page.ai("search for flights from Miami to LAX, select the cheapest option");”
  • [claimed-docs] https://hyperbrowser.ai/docs/agents/overview.md“Hyperbrowser lets you run powerful, AI-driven browser agents in managed cloud sessions. Whether you prefer open-source frameworks or cutting‑edge model-native agents, you can start tasks with a single API call and watch them execute live.”
  • [claimed-docs] https://hyperbrowser.ai/docs/agents/hyperagent“HyperAgent is our open-source tool that supercharges Playwright with AI.”
  • [claimed-docs] https://hyperbrowser.ai/docs/introduction.md“Built in support for Claude, OpenAI, Gemini, Grok, and BrowserUse agents.”

Operate the product with natural-language commandsweight 2

2 (weight) × 8 (quality) × 1.0 (full) = 16.0 of 20 max

  • [claimed-docs] https://hyperbrowser.ai/docs/hyperagent/quickstart“await page.ai("search for flights from Miami to LAX, select the cheapest option");”
  • [claimed-docs] https://hyperbrowser.ai/docs/hyperagent/overview.md“HyperAgent is an open-source browser automation framework that extends Playwright with AI capabilities. Write natural language commands instead of complex selectors”
  • [claimed-docs] https://hyperbrowser.ai/docs/hyperagent/extract“The `page.extract()` method pulls structured data from web pages. Define what you want using natural language and optionally enforce a schema with Zod for type-safe results.”
  • [claimed-docs] https://hyperbrowser.ai/docs/integrations/model-context-protocol“The Hyperbrowser MCP server provides a standardized interface for AI models to access powerful web automation capabilities like scraping, structured extraction, and crawling.”

Built-in AI = 41.8 ÷ 70 × 100 = 59.7

Automation9.0/100×0.15 of the PA blend

Depth of automation primitives — rules, scheduling, bulk operations, webhooks.

Perform bulk operations across many items at onceweight 2

2 (weight) × 6 (quality) × 0.6 (partial) = 7.2 of 20 max

  • [claimed-docs] https://hyperbrowser.ai/docs/web-scraping/crawl.md“The Crawl API allows you to crawl websites and get data from multiple pages in a single request. Starting from a URL, it can navigate through the site and extract content from linked pages.”
  • [claimed-docs] https://hyperbrowser.ai/docs/web-scraping/scrape.md“The Scrape API allows you to get the data you want from web pages with a single call. You can scrape page content and capture its data in various formats like markdown or html.”
  • [claimed-docs] https://hyperbrowser.ai/docs/web-scraping/extract.md“The Extract API allows you to extract structured data from web pages using AI. You can define a schema and prompt, and Hyperbrowser will extract the data matching your requirements.”
  • [community] https://news.ycombinator.com/item?id=42381712“Just did a pricing check, and you give twice as much concurrency/browsing/data-transfer as Browserbase. Nice!”

Define rules that trigger actions automatically on eventsweight 3

3 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 30 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Schedule recurring jobs or workflowsweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Version, review, and roll back my automationsweight 1

1 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 10 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Automation = 7.2 ÷ 80 × 100 = 9.0