Product

Steel

by Steel

Tier B 60/100

AI-native readiness · breakdown

Research coverage 58%

58%

Unresearched fields count as zero, so the grade rises as coverage does.

Visit Steel

Sandbox environment Yes

Built from public sources, with each change reviewed by a curator before it's accepted. How we check entries.

Entry updated Oct 30, 2026

Product website: https://steel.dev/
Documentation: https://docs.steel.dev/
Pricing: https://steel.dev/#pricing
Categories: Browser Automation

Description

Open-source headless browser API for agents (sessions, proxies, CAPTCHA); managed cloud and self-hostable.

AI-native score

How ready this product is for agents to use, on a 0–100 scale across four weighted dimensions. Security is one of them, so a high score is not a substitute for your own security or vendor-risk review. How is this scored?

Research coverage: 58% of the scored decision fields carry a confirmed value. Unresearched fields score zero in the grade above.

Component	Raw	Weight	Contribution
Integration	7/10	35%	24.5
Trust	3/6	30%	15.0
Portability	4/4	20%	20.0
Security	0/4	15%	0.0

Signals that fired

Integration: MCP server (+2) ; API spec, OpenAPI / gRPC / GraphQL (+1) ; Command-line interface (+1) ; SDK / developer kit (+1) ; Agent skill (+1) ; Verified llms.txt (+1)
Trust: Sandbox environment (yes, +2) ; Verified trust center (+1)
Portability: Open standards (+1) ; Standard protocol access (+1) ; No proprietary-SDK lock-in (+1) ; Self-hostable (+1) ; Open source (+1)

Signals not researched

These gaps cover the fields used in the AI-native score.

Integration surfaces: Headless signup, Native connectors
Trust & data policy: Multi-factor authentication, Zero data retention, No generative AI training, Hard budget caps, Data export, Data import, Documented provider swap
Security & compliance: Compliance certifications, Access controls

Trust & data policy

Trust center: Vendor trust center
Sandbox environment: Yes
Open standards: Yes
Standard protocol access: Yes
No proprietary-SDK lock-in: Yes
Self-hostable: Yes
Open source: Yes
Source code: https://github.com/steel-dev/steel-browser

Not yet researched Multi-factor authentication, Zero data retention, No generative AI training, Hard budget caps, Data export, Data import, Documented provider swap

What it does

Capabilities

Browser Automation

Drive a real or headless browser programmatically to perform tasks.

View 5 products
Web Scraping

Extract structured data from websites at scale.

View 11 products

Jobs to be done

From cited vendor documentation, each completion verdict says whether an agent can deliver the job's main outcome by and large through this product and which steps still need a person. Scope may limit cases or prerequisites while preserving that outcome. It's a separate axis from the AI-native score. Expand a job for the human steps, delegation, and scope. An unknown verdict means the answer is not yet established.

Automate a browser workflow Finishes end to end

Drive a multi-step task through a real browser on an agent's behalf.

Completion detail · via Command-line interface

Setup needs a human

Unknown

Per-task human step

None

On behalf of a principal

Supported

An agent drives a multi-step website form workflow for its principal through Steel CLI after installation and authenticated cloud setup. The documented sequence starts a named browser session, opens a page, inspects elements, fills and selects values, checks a box, clicks submit, waits for the resulting page state and stops the session.

Conditions: Requires the Steel CLI, authenticated cloud access and authority to use the target site. The documented route covers accessible forms; site-specific authentication, permissions and challenges can require additional handling. Cloud session time and concurrency limits depend on plan. Setup human requirement remains unknown.

View 3 products
Extract data from websites

Collect structured information from web pages for use by an application or agent.

View 9 products

Integration surfaces

How an agent connects to this product and finds its documentation. The largest dimension of the AI-native score (35%).

llms.txt: https://docs.steel.dev/llms.txt
WebMCP: No

MCP servers

Model Context Protocol endpoints an AI agent can connect to for this product's tools and data.

Steel MCP Server

API specs

Steel API
OpenAPI

Command-line interfaces

Steel CLI

Agent skills

Packaged skills an agent can load to operate this product.

Steel Browser

Developer kits

Steel Node SDK
Languages: JavaScript , TypeScript
Steel Python SDK
Languages: Python

Confirmed absent Agent2Agent (A2A) servers

Not yet researched Headless signup, Native connectors

Offers

Full pricing page

Plans

Scale

$250/mo

then $0.08 per browser_hour over the included allowance

then $6 per GB over the included allowance

then $1 per 1,000 successful_captcha_solves over the included allowance

then $5 per 1,000 browser_tool_calls over the included allowance

Includes $100 in usage credits each month, 100 concurrent browser sessions, sessions up to 1 hour, unlimited seats, 600 requests per minute and 14-day data retention. Includes a dedicated Slack channel and a HIPAA-ready BAA. Dedicated IPs are available separately.

Billing: Pay As You Go Subscription

Includes $100 in monthly usage credits applied to metered usage. Browser hours are billed by the minute, rounded up. Usage beyond included credits is billed at the plan rates.

View offer

Enterprise

Contact sales/mo

Includes 1,000 or more concurrent browser sessions and sessions up to 24 hours. Rates, included usage credits and limits are customized for the workload.

Custom monthly pricing plus usage. Contact sales for pricing and included usage credits.

View offer

Usage-based rates

Launch

Includes 10 concurrent browser sessions, sessions up to 15 minutes, up to 3 seats, 60 requests per minute and 7-day data retention.

Rate	Unit price
Launch	$0.10 per browser hour
Launch	$10 per GB
Launch	$3 per 1,000 CAPTCHA solves
LaunchApplies to /scrape, /screenshot and /pdf.	$5 per 1,000 browser tools calls

No monthly subscription fee. Includes $30 in one-time usage credits valid for 90 days, shared across browser time, proxy bandwidth, CAPTCHA solves and browser tools. Usage beyond credits is billed at the listed rates. Browser time is billed by the minute, rounded up. Managed proxies and CAPTCHA solving require $10 in paid balance. The deposit pays for usage.

View offer

Reviews

No approved reviews yet.

RSS: approved reviews

Catalog activity

Track how this entry changes as proposals are opened and merged.

RSS: merged changes · RSS: open proposals

Products from other publishers that share a job-to-be-done or category, most-shared first.

Browserbase by Browserbase Tier B

Same job: Automate a browser workflow Finishes end to end, Extract data from websites (not assessed)
Browserless by Browserless Tier B

Same job: Automate a browser workflow (not assessed), Extract data from websites Finishes end to end
Apify by Apify Tier B

Same job: Extract data from websites (not assessed)
ScrapingAnt by DATAANT SP. Z O.O. Tier D

Same job: Extract data from websites (not assessed)
Firecrawl by Firecrawl Tier A

Same job: Extract data from websites Finishes end to end
Diffbot Extract by Diffbot Tier C

Same job: Extract data from websites Finishes, delegation unknown

Own this product? Add a verified badge to your site

Show visitors and crawling agents your verified AI-native grade. The badge stays current as your entry is verified, and links back to this page.

Steel — AI-native Tier B (60/100) on Open Agent Guide

HTML

<a href="https://www.openagentguide.com/organizations/steel-dev/products/steel/?utm_source=badge&amp;utm_medium=referral">
  <img src="https://www.openagentguide.com/organizations/steel-dev/products/steel/badge.svg" alt="Steel — AI-native Tier B (60/100) on Open Agent Guide" height="64" />
</a>

Markdown

[![Steel — AI-native Tier B (60/100) on Open Agent Guide](https://www.openagentguide.com/organizations/steel-dev/products/steel/badge.svg?style=flat)](https://www.openagentguide.com/organizations/steel-dev/products/steel/?utm_source=badge&utm_medium=referral)

Make it agent-readable (optional JSON-LD)

Paste this schema.org Review beside the badge so agents resolve the grade to its source record, not just a picture.

<script type="application/ld+json">
{
  "@context": "https://schema.org",
  "@type": "Review",
  "itemReviewed": {
    "@type": "SoftwareApplication",
    "name": "Steel",
    "url": "https://steel.dev/"
  },
  "author": {
    "@type": "Organization",
    "name": "Open Agent Guide",
    "url": "https://openagentguide.com"
  },
  "reviewRating": {
    "@type": "Rating",
    "ratingValue": 60,
    "bestRating": 100,
    "worstRating": 0,
    "alternateName": "Tier B"
  },
  "url": "https://www.openagentguide.com/organizations/steel-dev/products/steel/"
}
</script>

The badge reflects only the verified tier and can’t be self-set. How scoring works

Ready to decide?

Tier B · 60/100 AI-native · 58% researched.

Visit Steel

Description

AI-native score

Trust & data policy

What it does

Capabilities

Jobs to be done

Integration surfaces

MCP servers

API specs

Command-line interfaces

Agent skills

Developer kits

Offers

Scale

Enterprise

Launch

Reviews

Catalog activity

Related products

Own this product? Add a verified badge to your site

HTML

Markdown

Ready to decide?