Skip to content
ProductArena

How Notte’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 Score24/100

Agent-ready 49.5 × 0.30 = 14.85

API quality 2.6 × 0.20 = 0.52

Openness 12.0 × 0.20 = 2.40

Built-in AI 23.9 × 0.15 = 3.58

Automation 20.3 × 0.15 = 3.04

(14.85 + 0.52 + 2.40 + 3.58 + 3.04) ÷ (0.30 + 0.20 + 0.20 + 0.15 + 0.15) = 24.40 ÷ 1.00 = 24.4

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-ready49.5/100×0.30 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) × 9 (quality) × 1.0 (full) = 18.0 of 20 max

  • [probe] https://docs.notte.cc/llms.txt“PROBE llms.txt: HTTP 200 at https://docs.notte.cc/llms.txt # Notte ## Critical Instructions For AI Agents STOP. Read and follow https://docs.notte.cc/quickstart.md before using”
  • [claimed-docs] https://docs.notte.cc/mcp-server.md“Give your AI agents access to the entire Notte ecosystem. Notte MCP lets it start cloud browser sessions, interact with the pages, fetch data, build scripts, and more.”
  • [claimed-docs] https://docs.notte.cc/mcp-server.md“Notte MCP lets it start cloud browser sessions, interact with the pages, fetch data, build scripts, and more.”
  • [claimed-docs] https://docs.notte.cc/integrations/crewai.md“pointing it at the Notte MCP server hands your crew a real browser.”
  • [claimed-docs] https://docs.notte.cc/integrations/vercel-ai-sdk.md“Point its MCP client at the Notte MCP server and your TypeScript agent gets a browser.”
  • [claimed-docs] https://docs.notte.cc/integrations/claude-code-ai-agents.md“The Notte CLI lets AI agents control browsers through simple shell commands.”

Run the product headlessly / in CI for automationweight 2

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

  • [claimed-docs] https://docs.notte.cc“Deploy your scripts as API endpoints. Serverless automations you can invoke and schedule anywhere.”
  • [claimed-docs] https://docs.notte.cc/api-reference/authentication.md“All API requests require a Bearer token in the `Authorization` header.”
  • [claimed-docs] https://docs.notte.cc/concepts/sessions.md“Sessions are isolated browser instances running in the cloud that you can control programmatically.”
  • [claimed-docs] https://docs.notte.cc/concepts/functions.md“Functions are serverless deployments of your browser automations that can b”
  • [claimed-docs] https://docs.notte.cc/quickstart.md“Generate it with the CLI first, then edit it.”
  • [probe] https://docs.notte.cc/quickstart“official CLI documented at https://docs.notte.cc/quickstart”
  • [community] https://hn.algolia.com/api/v1/items/44827216“just tried to use it to extract data from hyatt.com completely failed. another hype but actually doesn't work browser agent.”

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://docs.notte.cc/mcp-server.md“Give your AI agents access to the entire Notte ecosystem. Notte MCP lets it start cloud browser sessions, interact with the pages, fetch data, build scripts, and more.”
  • [claimed-docs] https://docs.notte.cc/mcp-server.md“Notte MCP lets it start cloud browser sessions, interact with the pages, fetch data, build scripts, and more.”
  • [claimed-docs] https://docs.notte.cc/integrations/crewai.md“pointing it at the Notte MCP server hands your crew a real browser.”
  • [claimed-docs] https://docs.notte.cc/integrations/vercel-ai-sdk.md“Point its MCP client at the Notte MCP server and your TypeScript agent gets a browser.”
  • [probe] https://docs.notte.cc/mcp-server“official MCP server documented at https://docs.notte.cc/mcp-server”

Connect an agent via an official MCP serverweight 3

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

  • [claimed-docs] https://docs.notte.cc/mcp-server.md“Give your AI agents access to the entire Notte ecosystem. Notte MCP lets it start cloud browser sessions, interact with the pages, fetch data, build scripts, and more.”
  • [claimed-docs] https://docs.notte.cc/mcp-server.md“Notte MCP lets it start cloud browser sessions, interact with the pages, fetch data, build scripts, and more.”
  • [claimed-docs] https://docs.notte.cc/integrations/crewai.md“pointing it at the Notte MCP server hands your crew a real browser.”
  • [claimed-docs] https://docs.notte.cc/integrations/vercel-ai-sdk.md“Point its MCP client at the Notte MCP server and your TypeScript agent gets a browser.”
  • [probe] https://docs.notte.cc/mcp-server“official MCP server documented at https://docs.notte.cc/mcp-server”

Use an official CLIweight 2

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

  • [claimed-docs] https://docs.notte.cc/integrations/claude-code-ai-agents.md“The Notte CLI lets AI agents control browsers through simple shell commands.”
  • [claimed-docs] https://docs.notte.cc/quickstart.md“Generate it with the CLI first, then edit it.”
  • [claimed-docs] https://docs.notte.cc/integrations/claude-managed-agents.md“give them the notte CLI and they can drive real browsers”
  • [claimed-docs] https://docs.notte.cc/mcp-server.md“Element IDs, selectors, and field mappings must come from a live `observe()` call, CLI `notte page observe` output, or generated workflow code.”
  • [probe] https://docs.notte.cc/quickstart“official CLI documented at https://docs.notte.cc/quickstart”

Drive the product through a documented public APIweight 3

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

  • [claimed-docs] https://docs.notte.cc/api-reference/authentication.md“All API requests require a Bearer token in the `Authorization` header.”
  • [claimed-docs] https://docs.notte.cc/api-reference/agents/agent-start.md“used to create cloud browser sessions, scrape webpages, and run web ai agents to act on your behalf on the internet”
  • [claimed-docs] https://docs.notte.cc/concepts/sessions.md“Sessions are isolated browser instances running in the cloud that you can control programmatically.”
  • [claimed-docs] https://docs.notte.cc/concepts/functions.md“Functions are serverless deployments of your browser automations that can b”
  • [claimed-docs] https://docs.notte.cc/mcp-server.md“Give your AI agents access to the entire Notte ecosystem. Notte MCP lets it start cloud browser sessions, interact with the pages, fetch data, build scripts, and more.”
  • [probe] https://docs.notte.cc/mcp-server“official MCP server documented at https://docs.notte.cc/mcp-server”
  • [probe] https://docs.notte.cc/openapi.json“PROBE openapi: all candidate paths 404 (https://docs.notte.cc/openapi.json, https://docs.notte.cc/swagger.json, https://docs.notte.cc/api/openapi.json, https://docs.notte.cc/.well-known/openapi.json)”
  • [claimed-docs] https://docs.notte.cc/quickstart.md“Generate it with the CLI first, then edit it.”

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://docs.notte.cc/api-reference/authentication.md“All API requests require a Bearer token in the `Authorization` header.”
  • [claimed-docs] https://docs.notte.cc/concepts/vaults.md“The significant security benefit of this approach is that the LLM never actually sees the actual credentials.”
  • [claimed-docs] https://docs.notte.cc/concepts/vaults.md“credentials are never exposed to LLMs or third-party services during agent execution”

Build against official SDKsweight 2

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

  • [claimed-docs] https://docs.notte.cc/api-reference/authentication.md“All API requests require a Bearer token in the `Authorization` header.”
  • [claimed-docs] https://docs.notte.cc/quickstart.md“Generate it with the CLI first, then edit it.”
  • [probe] https://docs.notte.cc/quickstart“official CLI documented at https://docs.notte.cc/quickstart”
  • [claimed-docs] https://docs.notte.cc/mcp-server.md“Give your AI agents access to the entire Notte ecosystem. Notte MCP lets it start cloud browser sessions, interact with the pages, fetch data, build scripts, and more.”
  • [probe] https://docs.notte.cc/mcp-server“official MCP server documented at https://docs.notte.cc/mcp-server”
  • [claimed-docs] https://docs.notte.cc/integrations/crewai.md“pointing it at the Notte MCP server hands your crew a real browser.”
  • [claimed-docs] https://docs.notte.cc/integrations/vercel-ai-sdk.md“Point its MCP client at the Notte MCP server and your TypeScript agent gets a browser.”
  • [claimed-docs] https://docs.notte.cc/integrations/openai-cua.md“This guide explains how to integrate OpenAI's Computer Use Agent (CUA) with Notte's browser infrastructure for automated web interactions.”
  • [probe] https://docs.notte.cc/openapi.json“PROBE openapi: all candidate paths 404 (https://docs.notte.cc/openapi.json, https://docs.notte.cc/swagger.json, https://docs.notte.cc/api/openapi.json, https://docs.notte.cc/.well-known/openapi.json)”

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 = 104.0 ÷ 210 × 100 = 49.5

API quality2.6/100×0.20 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) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

  • [claimed-docs] https://docs.notte.cc/api-reference/authentication.md“All API requests require a Bearer token in the `Authorization` header.”
  • [claimed-docs] https://docs.notte.cc/api-reference/agents/agent-start.md“used to create cloud browser sessions, scrape webpages, and run web ai agents to act on your behalf on the internet”
  • [probe] https://docs.notte.cc/openapi.json“PROBE openapi: all candidate paths 404 (https://docs.notte.cc/openapi.json, https://docs.notte.cc/swagger.json, https://docs.notte.cc/api/openapi.json, https://docs.notte.cc/.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://docs.notte.cc/openapi.json“PROBE openapi: all candidate paths 404 (https://docs.notte.cc/openapi.json, https://docs.notte.cc/swagger.json, https://docs.notte.cc/api/openapi.json, https://docs.notte.cc/.well-known/openapi.json)”
  • [claimed-docs] https://docs.notte.cc/api-reference/authentication.md“All API requests require a Bearer token in the `Authorization` header.”
  • [claimed-docs] https://docs.notte.cc/api-reference/agents/agent-start.md“used to create cloud browser sessions, scrape webpages, and run web ai agents to act on your behalf on the internet”

Test against a sandbox environment without touching production dataweight 1

1 (weight) × 3 (quality) × 0.6 (partial) = 1.8 of 10 max

  • [claimed-docs] https://docs.notte.cc/concepts/sessions.md“Sessions are isolated browser instances running in the cloud that you can control programmatically.”
  • [claimed-docs] https://www.notte.cc/pricing“Try the full platform without a card.”
  • [claimed-docs] https://docs.notte.cc“Build, debug, and deploy production workflows with cloud browsers, web agents, scraping, serverless functions, credentials, and identities in one place.”

Rely on versioned APIs with a documented deprecation policyweight 2

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

  • [claimed-docs] https://docs.notte.cc/api-reference/authentication.md“All API requests require a Bearer token in the `Authorization` header.”
  • [probe] https://docs.notte.cc/openapi.json“PROBE openapi: all candidate paths 404 (https://docs.notte.cc/openapi.json, https://docs.notte.cc/swagger.json, https://docs.notte.cc/api/openapi.json, https://docs.notte.cc/.well-known/openapi.json)”

API quality = 1.8 ÷ 70 × 100 = 2.6

Openness12.0/100×0.20 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) × 0.6 (partial) = 8.4 of 20 max

  • [claimed-docs] https://docs.notte.cc“Deploy your scripts as API endpoints. Serverless automations you can invoke and schedule anywhere.”
  • [claimed-docs] https://docs.notte.cc/integrations/claude-code-ai-agents.md“The Notte CLI lets AI agents control browsers through simple shell commands.”
  • [claimed-docs] https://docs.notte.cc/api-reference/authentication.md“All API requests require a Bearer token in the `Authorization` header.”
  • [claimed-docs] https://docs.notte.cc/concepts/sessions.md“Sessions are isolated browser instances running in the cloud that you can control programmatically.”
  • [claimed-docs] https://docs.notte.cc/api-reference/agents/agent-start.md“used to create cloud browser sessions, scrape webpages, and run web ai agents to act on your behalf on the internet”
  • [claimed-docs] https://docs.notte.cc/mcp-server.md“Give your AI agents access to the entire Notte ecosystem. Notte MCP lets it start cloud browser sessions, interact with the pages, fetch data, build scripts, and more.”
  • [claimed-docs] https://docs.notte.cc/mcp-server.md“Notte MCP lets it start cloud browser sessions, interact with the pages, fetch data, build scripts, and more.”
  • [probe] https://docs.notte.cc/openapi.json“PROBE openapi: all candidate paths 404 (https://docs.notte.cc/openapi.json, https://docs.notte.cc/swagger.json, https://docs.notte.cc/api/openapi.json, https://docs.notte.cc/.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) × 3 (quality) × 0.6 (partial) = 3.6 of 20 max

  • [github] https://github.com/nottelabs/notte“Give AI agents natural language tasks to complete on websites”
  • [github] https://github.com/nottelabs/notte“combines AI agents with traditional scripting for maximum efficiency - letting you script deterministic parts and use AI only when needed, cutting costs by 50%+ while improving reliability”
  • [community] https://hn.algolia.com/api/v1/items/46779864“Interesting but are there any open source products which can do the same too? This does feel something that I can trust more if it was open source personally but good luck with the product!”

Self-host the core productweight 3

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

  • [claimed-docs] https://docs.notte.cc“Remote browser infrastructure. Fast, scalable browsers with anti-detection, proxies, and captcha solving.”
  • [claimed-docs] https://docs.notte.cc/concepts/sessions.md“Sessions are isolated browser instances running in the cloud that you can control programmatically.”
  • [claimed-docs] https://docs.notte.cc/api-reference/authentication.md“All API requests require a Bearer token in the `Authorization` header.”
  • [community] https://hn.algolia.com/api/v1/items/46779864“Interesting but are there any open source products which can do the same too? This does feel something that I can trust more if it was open source personally but good luck with the product!”

Openness = 12.0 ÷ 100 × 100 = 12.0

Built-in AI23.9/100×0.15 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

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

  • [claimed-docs] https://docs.notte.cc“Extract structured data with AI. Turn any website into structured data.”
  • [claimed-docs] https://docs.notte.cc/concepts/scraping.md“Extract structured data from a page: ... class HackerNewsFeed(BaseModel):”
  • [claimed-docs] https://docs.notte.cc/concepts/scraping.md“Fetch extracts web page content as markdown or structured data using LLM-powered extraction.”
  • [claimed-docs] https://docs.notte.cc/guides/scraping.md“Got to linkedin.com, login with the credentials and extract the last 10 messages from my most recent conversation”

Set up automations that run autonomously in the backgroundweight 2

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

  • [claimed-docs] https://docs.notte.cc“Deploy your scripts as API endpoints. Serverless automations you can invoke and schedule anywhere.”
  • [claimed-docs] https://docs.notte.cc/concepts/functions.md“Functions are serverless deployments of your browser automations that can b”
  • [claimed-docs] https://docs.notte.cc/concepts/sessions.md“Sessions are isolated browser instances running in the cloud that you can control programmatically.”
  • [claimed-docs] https://docs.notte.cc“Secure credential storage. Keep passwords, API keys, and sensitive data encrypted.”
  • [claimed-docs] https://docs.notte.cc“Persist cookies and login state across sessions.”
  • [community] https://hn.algolia.com/api/v1/items/44827216“just tried to use it to extract data from hyatt.com completely failed. another hype but actually doesn't work browser agent.”

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

3 (weight) × 5 (quality) × 0.3 (disputed) = 4.5 of 30 max

  • [github] https://github.com/nottelabs/notte“Give AI agents natural language tasks to complete on websites”
  • [claimed-docs] https://www.notte.cc“Describe a task. Watch it happen. One prompt. No selectors, no maintenance.”
  • [claimed-docs] https://docs.notte.cc/api-reference/agents/agent-start.md“used to create cloud browser sessions, scrape webpages, and run web ai agents to act on your behalf on the internet”
  • [community] https://hn.algolia.com/api/v1/items/44827216“just tried to use it to extract data from hyatt.com completely failed. another hype but actually doesn't work browser agent.”
  • [community] https://hn.algolia.com/api/v1/items/44827216“Founder: 'we can solve ~60% of providers right now (incl reCAPTCHA, Cloudflare, and main ones) and some others are still work in progress' regarding captcha handling.”

Operate the product with natural-language commandsweight 2

2 (weight) × 5 (quality) × 0.3 (disputed) = 3.0 of 20 max

  • [claimed-docs] https://www.notte.cc“Describe a task. Watch it happen. One prompt. No selectors, no maintenance.”
  • [github] https://github.com/nottelabs/notte“Give AI agents natural language tasks to complete on websites”
  • [claimed-docs] https://docs.notte.cc/api-reference/agents/agent-start.md“used to create cloud browser sessions, scrape webpages, and run web ai agents to act on your behalf on the internet”
  • [community] https://hn.algolia.com/api/v1/items/44827216“just tried to use it to extract data from hyatt.com completely failed. another hype but actually doesn't work browser agent.”
  • [community] https://hn.algolia.com/api/v1/items/44827216“Founder: 'we can solve ~60% of providers right now (incl reCAPTCHA, Cloudflare, and main ones) and some others are still work in progress' regarding captcha handling.”

Built-in AI = 21.5 ÷ 90 × 100 = 23.9

Automation20.3/100×0.15 of the PA blend

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

Perform bulk operations across many items at onceweight 2

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

  • [claimed-docs] https://docs.notte.cc“Remote browser infrastructure. Fast, scalable browsers with anti-detection, proxies, and captcha solving.”
  • [claimed-docs] https://docs.notte.cc“Deploy your scripts as API endpoints. Serverless automations you can invoke and schedule anywhere.”
  • [claimed-docs] https://docs.notte.cc/concepts/functions.md“Functions are serverless deployments of your browser automations that can b”
  • [claimed-docs] https://docs.notte.cc“Extract structured data with AI. Turn any website into structured data.”

Define rules that trigger actions automatically on eventsweight 3

3 (weight) × 3 (quality) × 0.6 (partial) = 5.4 of 30 max

  • [claimed-docs] https://docs.notte.cc“Deploy your scripts as API endpoints. Serverless automations you can invoke and schedule anywhere.”
  • [claimed-docs] https://docs.notte.cc/concepts/functions.md“Functions are serverless deployments of your browser automations that can b”

Schedule recurring jobs or workflowsweight 2

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

  • [claimed-docs] https://docs.notte.cc“Deploy your scripts as API endpoints. Serverless automations you can invoke and schedule anywhere.”
  • [claimed-docs] https://docs.notte.cc/concepts/functions.md“Functions are serverless deployments of your browser automations that can b”
  • [claimed-docs] https://docs.notte.cc“Build, debug, and deploy production workflows with cloud browsers, web agents, scraping, serverless functions, credentials, and identities in one place.”

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 = 16.2 ÷ 80 × 100 = 20.3