44
/100
prowl
Benchmarked Sep 01, 2026

Browser Use

Open-source web agent for AI

ai platform_profile
Benchmark Your API

Score Breakdown

Latency 6/10
Auth Simplicity 6/10
Parseability 6/10
Consistency 5/10
Documentation 5/10
Error Clarity 4/10
First-Try Success 4/10
Token Efficiency 3/10

Benchmark Analysis Log

Full LLM thinking from the 4-phase benchmark pipeline.

Analyze
{
  "service_type": "platform",
  "base_url": "https://browseruse.dev",
  "auth_method": "none",
  "auth_config": {},
  "endpoints": [],
  "pricing_model": {
    "type": "unknown",
    "details": {
      "open_source": true,
      "self_hosted": true,
      "pricing_not_documented_on_page"
    }
  },
  "rate_limits": {},
  "capabilities": [
    "Web automation",
    "AI agent integration",
    "Browser control",
    "Task execution",
    "Open-source library",
    "Self-hosting",
    "API for agent interoperability"
  ],
  "raw_analysis": "The service is an open-source web agent platform named 'Browser Use' located at https://browseruse.dev. It is designed to enable AI to control a web browser, likely for automation tasks such as form filling, navigation, and data extraction. The provided content is essentially a GitHub page (html), indicating the project is hosted on GitHub, with extensive feature flags and environment configurations typical of a GitHub repository. The platform appears to be a developer tool that integrates with AI systems, allowing them to interact with websites programmatically. There is no documented public API endpoint since the service is primarily a library/tool that developers use within their own applications, likely interacting with the browser via Playwright or similar. Authentication is not required for the core library, but users may need to authenticate to the GitHub repository or their own AI services. The maturity is moderate-high given its GitHub presence and active development. Integration is through code, with Python/JS libraries, and it can be used with various AI models. The pricing model is open-source, free to use, and self-hosted, with no explicit pricing page found. Rate limits are not applicable as it is a local library, though usage of external AI services may have their own limits."
}
Execute

3/3 tests passed

TestEndpointStatusLatency
website_uptimeGET /200814ms
robots_txtGET /robots.txt200210ms
llms_txtGET /llms.txt200623ms
Interpret
```json
{
  "overall": 42,
  "dimensions": {
    "token_efficiency": 3.0,
    "first_try_success": 4.0,
    "response_parseability": 6.0,
    "error_clarity": 4.0,
    "doc_quality": 5.0,
    "auth_simplicity": 6.0,
    "latency": 6.0,
    "consistency": 5.0
  },
  "pricing_normalized": {},
  "issues": [
    "No capabilities or pricing model data available in platform analysis",
    "No llms.txt file detected - site serves generic HTML instead of structured agent documentation",
    "Robots.txt check returned generic HTML rather than actual robots directives",
    "No structured API documentation or agent-specific endpoints discovered",
    "Value proposition unclear from available data - no feature descriptions or use cases provided"
  ],
  "recommendations": [
    "Add an llms.txt file with clear API/agent documentation, capabilities, and onboarding steps",
    "Provide structured JSON metadata about features, pricing tiers, and integration options",
    "Document authentication methods and API response formats for programmatic access",
    "Create a getting-started quickstart guide specifically targeting AI agents",
    "Expose a machine-readable capabilities manifest for automated discovery"
  ]
}
```

Agent Readiness

x402 Payments
Not supported
Streaming
No
Sandbox
None
Agent Auth
Unknown
SDKs
None listed
MCP Support
No

Embed your Prowl badge

Show your live agent-readiness score on your own site. Free, no auth — it updates as your score changes.

Prowl agent-readiness badge
<a href="https://prowl.world/service/browser-use">
  <img src="https://prowl.world/badge/browser-use.svg" height="56" alt="Agent-readiness on Prowl">
</a>

Options: ?style=light|dark · ?size=sm|md · ?variant=certified (claimed + DNS-verified only) · badge generator with preview

Want the full interactive view?

See operational metrics, LLM evaluations, agent readiness, and more.

Open in Dashboard