# All Products

Showing 1–9 of 9 products. Page 1 of 1.
Sort: score.

Filter options: [Capability](#capability) · [Job to be done](#job-to-be-done) · [AI-native tier](#ai-native-tier) · [Billing model](#billing-model) · [Integrations](#integrations) · [Task completion](#filter-by-documented-task-completion).

The AI-native score listed for each product rates how ready it is for agents to use, from 0 to 100. A high score is not a substitute for your own security or vendor-risk review. See [how scoring works](/methodology/).
Each row also lists Free plan. Yes means the product has an active offer with a free pricing option, alongside any paid plans. Unknown means no free offer is recorded, which is not a confirmed no — filter with `free_plan=true` and add `expand=offers` to read the terms, quotas, and eligibility.

**Applied filters:**
- job_to_be_done_slug=extract-data-from-websites

[Clear filters](/products.md)


- [Firecrawl](/organizations/firecrawl/products/firecrawl/) by [Firecrawl](/organizations/firecrawl/) — API that crawls and scrapes websites, returning clean LLM-ready markdown and structured data. Its Search API costs 2 credits per 10 results, rounded up. Adding scrapeOptions returns page …
  - Selected job: Extract data from websites (`extract-data-from-websites`): ✓ Finishes end to end. Scope: Collect structured information from web pages for use by an application or agent through the Firecrawl Extract API: submit one or more URLs with a prompt or JSON schema, then poll the returned job id for the completed structured data. Route: API. Conditions: The Extract endpoint (/extract) is in beta, and Firecrawl documents /agent as its successor. Single-request coverage of very large sites and exhaustive time-filtered enumeration are not supported. Extraction results are retrievable by job id for 24 hours after completion.
  - Categories: [Search-Grounded LLM API](/categories/search-grounded-llm-api/), [Web Data for Agents](/categories/web-data-for-agents/)
  - AI-native score: 83/100 (Tier A)
  - Free plan: Yes

- [Apify](/organizations/apify/products/apify/) by [Apify](/organizations/apify/) — Platform for running web scraping and browser automation jobs and serving their data to agents and applications.
  - Selected job: Extract data from websites (`extract-data-from-websites`): Not yet assessed for this job.
  - Categories: [Browser Automation](/categories/browser-automation/), [Web Data for Agents](/categories/web-data-for-agents/)
  - AI-native score: 67/100 (Tier B)
  - Free plan: Yes

- [Browserbase](/organizations/browserbase/products/browserbase/) by [Browserbase](/organizations/browserbase/) — Managed remote Chromium driven via Playwright/Puppeteer/CDP, with stealth mode and CAPTCHA solving; billed by browser-time.
  - Selected job: Extract data from websites (`extract-data-from-websites`): Not yet assessed for this job.
  - Categories: [Browser Automation](/categories/browser-automation/)
  - AI-native score: 67/100 (Tier B)
  - Free plan: Yes
  - Other assessed jobs:
    - ✓ Finishes end to end: Automate a browser workflow (`automate-browser-workflow`, API)
- [Steel](/organizations/steel-dev/products/steel/) by [Steel](/organizations/steel-dev/) — Open-source headless browser API for agents (sessions, proxies, CAPTCHA); managed cloud and self-hostable.
  - Selected job: Extract data from websites (`extract-data-from-websites`): Not yet assessed for this job.
  - Categories: [Browser Automation](/categories/browser-automation/)
  - AI-native score: 60/100 (Tier B)
  - Free plan: Unknown
  - Other assessed jobs:
    - ✓ Finishes end to end: Automate a browser workflow (`automate-browser-workflow`, CLI)
- [Browserless](/organizations/browserless/products/browserless/) by [Browserless](/organizations/browserless/) — Browser-as-a-service exposing REST /content, /scrape, and /unblock endpoints plus CDP; self-hostable via Docker.
  - Selected job: Extract data from websites (`extract-data-from-websites`): ✓ Finishes end to end. Scope: An application or agent collects structured information from a web page for its principal through Browserless POST /scrape after API-token setup. The caller supplies the URL and CSS selectors; Browserless renders the page and returns matching text, HTML and attributes as JSON. Route: API. Conditions: Requires a Browserless API token, accessible target page and matching CSS selectors. Bot detection, blocked pages or missing selectors can prevent extraction. Additional stealth, proxy or CAPTCHA handling can require a different route and add usage charges. This record covers the documented extraction request, with setup human requirement left unknown.
  - Categories: [Browser Automation](/categories/browser-automation/)
  - AI-native score: 55/100 (Tier B)
  - Free plan: Unknown

- [Diffbot Extract](/organizations/diffbot/products/diffbot-extract/) by [Diffbot](/organizations/diffbot/) — ML-based structured extraction (Article/Product/etc.) returning clean fields from a URL, with JS rendering.
  - Selected job: Extract data from websites (`extract-data-from-websites`): ◇ Finishes, delegation unknown. Scope: For a developer's application, collect structured information from web pages using Diffbot Extract after API-token setup. The caller sends a URL and token in a GET request; Diffbot renders and classifies the page and returns structured JSON objects. Route: API. Conditions: Analyze selects a page-type extractor automatically; dedicated endpoints cover specified page types such as articles and products. Extract consumes one credit per request, or two when a proxy is used. Human setup, human execution and on-behalf-of assessments remain unknown.
  - Categories: [Document AI & Extraction](/categories/document-ai-extraction/), [Web Data for Agents](/categories/web-data-for-agents/)
  - AI-native score: 41/100 (Tier C)
  - Free plan: Unknown

- [ScrapingAnt](/organizations/dataant/products/scrapingant/) by [DATAANT SP. Z O.O.](/organizations/dataant/) — Web scraping API for retrieving website content.
  - Selected job: Extract data from websites (`extract-data-from-websites`): Not yet assessed for this job.
  - Categories: [Browser Automation](/categories/browser-automation/), [Web Data for Agents](/categories/web-data-for-agents/)
  - AI-native score: 26/100 (Tier D)
  - Free plan: Unknown

- [Bright Data Web Unlocker](/organizations/bright-data/products/web-unlocker/) by [Bright Data](/organizations/bright-data/) — Automated unblocking API that returns page HTML from heavily protected sites; pairs with a CDP Scraping Browser.
  - Selected job: Extract data from websites (`extract-data-from-websites`): Not yet assessed for this job.
  - Categories: [Web Data for Agents](/categories/web-data-for-agents/)
  - AI-native score: Unrated (38/100 researched)
  - Free plan: Unknown

- [Zyte API](/organizations/zyte/products/zyte-api/) by [Zyte](/organizations/zyte/) — Unified extraction API with automatic ban handling and browser rendering, priced by site difficulty and billed only on success.
  - Selected job: Extract data from websites (`extract-data-from-websites`): Not yet assessed for this job.
  - Categories: [Web Data for Agents](/categories/web-data-for-agents/)
  - AI-native score: Unrated (38/100 researched)
  - Free plan: Unknown


## Filter reference

Parameters apply to this page and the JSON product API. Repeat a multi-value parameter to match any selected value. Different filters must all match. Filter links preserve other active parameters and reset pagination.

### Capability

`capability_slug` accepts capability slugs from the [capability catalog (JSON)](/api/v1/catalog/capabilities/). This catalog lists what products can do.

### Job to be done

`job_to_be_done_slug` accepts job slugs from the [job catalog (JSON)](/api/v1/catalog/jobs-to-be-done/), including jobs without completion assessments. Free-text search uses `search`, for example [search for web search](?job_to_be_done_slug=extract-data-from-websites&search=web+search).

### AI-native tier

`tier` accepts [S](?job_to_be_done_slug=extract-data-from-websites&tier=S), [A](?job_to_be_done_slug=extract-data-from-websites&tier=A), [B](?job_to_be_done_slug=extract-data-from-websites&tier=B), [C](?job_to_be_done_slug=extract-data-from-websites&tier=C), [D](?job_to_be_done_slug=extract-data-from-websites&tier=D), or [Unrated](?job_to_be_done_slug=extract-data-from-websites&tier=Unrated). A tier rates general agent readiness. Check the selected job's assessment for task completion.

### Billing model

`billing_model` accepts slugs from the [billing model catalog (JSON)](/api/v1/catalog/billing-models/). It filters by charging structure. Offer terms determine the cost of a workload.

Related plan filters: [Free plan](?job_to_be_done_slug=extract-data-from-websites&free_plan=true) (`free_plan=true`) and [Pay-as-you-go](?job_to_be_done_slug=extract-data-from-websites&pay_go=true) (`pay_go=true`).

### Integrations

Boolean filters accept `true` or `false`: `has_mcp`, `has_a2a`, `has_cli`, `has_api_spec`, and `has_sdk`. For example, [products with an API specification and SDK](?job_to_be_done_slug=extract-data-from-websites&has_api_spec=true&has_sdk=true).

## Filter by documented task completion

These filters narrow results by whether an agent can finish the job, its route, delegation support, and required human steps. All completion facets match one assessed job and route. Use `job_to_be_done_slug` to choose a job. The list below contains only jobs with documented assessments.

- Completion support (`completion_support`): [Documented complete](?job_to_be_done_slug=extract-data-from-websites&completion_support=documented_complete) (`documented_complete`), [Documented partial](?job_to_be_done_slug=extract-data-from-websites&completion_support=documented_partial) (`documented_partial`)

- Completion route (`route_kind`): [API](?job_to_be_done_slug=extract-data-from-websites&route_kind=api) (`api`), [MCP server](?job_to_be_done_slug=extract-data-from-websites&route_kind=mcp) (`mcp`), [A2A server](?job_to_be_done_slug=extract-data-from-websites&route_kind=a2a) (`a2a`), [Command-line interface](?job_to_be_done_slug=extract-data-from-websites&route_kind=cli) (`cli`), [SDK / developer kit](?job_to_be_done_slug=extract-data-from-websites&route_kind=sdk) (`sdk`), [WebMCP](?job_to_be_done_slug=extract-data-from-websites&route_kind=webmcp) (`webmcp`), [Agent skill](?job_to_be_done_slug=extract-data-from-websites&route_kind=agent_skill) (`agent_skill`), [Native connector](?job_to_be_done_slug=extract-data-from-websites&route_kind=native_connector) (`native_connector`), [Web UI (browser/computer use)](?job_to_be_done_slug=extract-data-from-websites&route_kind=web) (`web`), [Documented route without a published spec](?job_to_be_done_slug=extract-data-from-websites&route_kind=prose) (`prose`)

- Acting on behalf of a user (`on_behalf_of`): [Supported](?job_to_be_done_slug=extract-data-from-websites&on_behalf_of=supported) (`supported`), [Conditional](?job_to_be_done_slug=extract-data-from-websites&on_behalf_of=conditional) (`conditional`), [Prohibited](?job_to_be_done_slug=extract-data-from-websites&on_behalf_of=prohibited) (`prohibited`)

- Per-task human step (`execution_human_requirement`): [None](?job_to_be_done_slug=extract-data-from-websites&execution_human_requirement=none) (`none`), [Required](?job_to_be_done_slug=extract-data-from-websites&execution_human_requirement=required) (`required`), [Conditional](?job_to_be_done_slug=extract-data-from-websites&execution_human_requirement=conditional) (`conditional`)

Jobs with documented assessments:
- [Accept online payments](?job_to_be_done_slug=accept-online-payments) (`accept-online-payments`)
- [Add authentication to an app](?job_to_be_done_slug=add-authentication-to-app) (`add-authentication-to-app`)
- [Automate a browser workflow](?job_to_be_done_slug=automate-browser-workflow) (`automate-browser-workflow`)
- [Automate household devices](?job_to_be_done_slug=automate-household-devices) (`automate-household-devices`)
- [Build AI agents](?job_to_be_done_slug=build-ai-agents) (`build-ai-agents`)
- [Capture and complete personal tasks](?job_to_be_done_slug=capture-and-complete-personal-tasks) (`capture-and-complete-personal-tasks`)
- [Check weather for an outing or trip](?job_to_be_done_slug=check-weather-for-outing-or-trip) (`check-weather-for-outing-or-trip`)
- [Compare flight options](?job_to_be_done_slug=compare-flight-options) (`compare-flight-options`)
- [Compare marketing channel performance](?job_to_be_done_slug=compare-marketing-channel-performance) (`compare-marketing-channel-performance`)
- [Create Agent Email Inbox](?job_to_be_done_slug=create-agent-email-inbox) (`create-agent-email-inbox`)
- [Create UGC video ads](?job_to_be_done_slug=create-ugc-video-ads) (`create-ugc-video-ads`)
- [Create and send invoices](?job_to_be_done_slug=create-and-send-invoices) (`create-and-send-invoices`)
- [Deploy an application to the cloud](?job_to_be_done_slug=deploy-application-to-cloud) (`deploy-application-to-cloud`)
- [Enrich B2B contact records](?job_to_be_done_slug=enrich-b2b-contact-records) (`enrich-b2b-contact-records`)
- [Extract data from websites](?job_to_be_done_slug=extract-data-from-websites) (`extract-data-from-websites`)
- [Find a person's business email address](?job_to_be_done_slug=find-business-email-address) (`find-business-email-address`)
- [Find and compare hotels](?job_to_be_done_slug=find-and-compare-hotels) (`find-and-compare-hotels`)
- [Generate a logo or brand image](?job_to_be_done_slug=generate-brand-image) (`generate-brand-image`)
- [Manage a household budget](?job_to_be_done_slug=manage-household-budget) (`manage-household-budget`)
- [Manage a sales pipeline](?job_to_be_done_slug=manage-sales-pipeline) (`manage-sales-pipeline`)
- [Manage advertising campaigns programmatically](?job_to_be_done_slug=manage-advertising-campaigns-programmatically) (`manage-advertising-campaigns-programmatically`)
- [Manage customer support](?job_to_be_done_slug=manage-customer-support) (`manage-customer-support`)
- [Manage project work](?job_to_be_done_slug=manage-project-work) (`manage-project-work`)
- [Plan a local journey](?job_to_be_done_slug=plan-a-local-journey) (`plan-a-local-journey`)
- [Plan meals with nutrition information](?job_to_be_done_slug=plan-meals-with-nutrition-information) (`plan-meals-with-nutrition-information`)
- [Research a topic in depth](?job_to_be_done_slug=research-a-topic-in-depth) (`research-a-topic-in-depth`)
- [Research website traffic](?job_to_be_done_slug=research-website-traffic) (`research-website-traffic`)
- [Reserve a restaurant table](?job_to_be_done_slug=reserve-restaurant-table) (`reserve-restaurant-table`)
- [Retain agent memory across sessions](?job_to_be_done_slug=retain-agent-memory) (`retain-agent-memory`)
- [Review business financial reports](?job_to_be_done_slug=review-business-financial-reports) (`review-business-financial-reports`)
- [Route requests across language models](?job_to_be_done_slug=route-llm-requests) (`route-llm-requests`)
- [Schedule meetings](?job_to_be_done_slug=schedule-meetings) (`schedule-meetings`)
- [Search the web](?job_to_be_done_slug=search-web) (`search-web`)
- [Send SMS programmatically](?job_to_be_done_slug=send-sms-programmatically) (`send-sms-programmatically`)
- [Send transactional email](?job_to_be_done_slug=send-transactional-email) (`send-transactional-email`)
- [Synthesize speech from text](?job_to_be_done_slug=synthesize-speech-from-text) (`synthesize-speech-from-text`)

---
Agents: install the `open-agent-guide` skill or register the MCP server at `/mcp` to keep this catalog on hand across sessions. Sign up at `/api/v1/users/signup/` to raise your rate limits and unlock catalog corrections, product following, and decision callbacks.

Content licensed under [CC BY-SA 4.0](https://creativecommons.org/licenses/by-sa/4.0/).