Websites, through a bot’s eyes.

Every published report from our scanner, ranked by how well language models and agents can read each site.

How websites are scored

Signals

Each one you pick narrows the list: a site must have them all.

Agent capabilities

API catalog3Lists the site's public APIs in one standard place, so an agent can find and use them without reading the docs. A bonus: it earns a badge and never costs points.
auth.md1A simple file that tells AI agents how to sign in and get access. A bonus: it earns a badge and never costs points.
A2A agent card1Describes the site's own AI agent in the A2A format, so other agents can find it and hand it work. A bonus: it earns a badge and never costs points.
Agent Skills index1Lists reusable instructions the site publishes for AI agents, with descriptions and download locations. The index earns a badge; the skill downloads themselves are not verified.
Web Bot Auth1Publishes the keys the site's own bots sign their requests with, so other websites can verify them. The badge checks the keys; the bots' requests are not observed.
ACP commerce1Publishes how agents can connect to its Agentic Commerce Protocol integration. The badge confirms discovery metadata; purchases are not tested.

Standards

llms.txt24A short guide to the site written for AI models: what it is and which pages matter most.
robots.txt33The file that tells crawlers where they may go. Every other rule a site gives to bots starts here.
Sitemap33A list of the site's pages, so a bot sees everything that exists instead of guessing from links.
Descriptive llms.txt16The llms.txt describes what is behind each link, so a model knows which pages are worth reading.
llms-full.txt or .md pages12The content is also available as plain Markdown, in one llms-full.txt file or as separate .md pages. Models can read it without the HTML.
Markdown negotiation3Pages come back as clean Markdown when a bot asks for it: just the content, without menus, styling and scripts.
AI crawler rules13The site says which AI bots may visit, for training, search or answering questions. Blocking some is fine; what counts is making a choice.
Content Signals3The site says how its content may be used: for search, in AI answers or to train AI. Any mix of yes and no counts.
schema.org JSON-LD24Structured data on the homepage says what the site is, such as a company, a product or an article, so machines don't have to guess.
Semantic HTML14The page has a clear structure: a main content area, headings in order, a header and a footer. A bot can tell the content from the rest.
Crawlable navigation24Observed homepage navigation exposes usable page addresses and section targets in HTML. Destinations are not fetched by this check.
Named links and buttons30Links and buttons in the collected homepage HTML have names recoverable from text, labels or native alternatives, including icon controls.
Named form fields10Observed homepage fields have recoverable names and recognizable input semantics. Submission behavior is not tested.
Control roles and states26Homepage controls meet static checks for roles, required states and relationship targets, using native HTML semantics where available.
Typed links3The page links to versions made for machines, such as a Markdown copy or an API description, so an agent can go straight to them.
Canonical URL31Each page names the one address that should be indexed and cited, so an agent quoting it links to the right URL.
Working section links13Links to part of a page, such as a table of contents or a skip link, lead to that section instead of the top of the page.

Filters · 1 active

Signals

Each one you pick narrows the list: a site must have them all.

Agent capabilities

API catalog3Lists the site's public APIs in one standard place, so an agent can find and use them without reading the docs. A bonus: it earns a badge and never costs points.
auth.md1A simple file that tells AI agents how to sign in and get access. A bonus: it earns a badge and never costs points.
A2A agent card1Describes the site's own AI agent in the A2A format, so other agents can find it and hand it work. A bonus: it earns a badge and never costs points.
Agent Skills index1Lists reusable instructions the site publishes for AI agents, with descriptions and download locations. The index earns a badge; the skill downloads themselves are not verified.
Web Bot Auth1Publishes the keys the site's own bots sign their requests with, so other websites can verify them. The badge checks the keys; the bots' requests are not observed.
ACP commerce1Publishes how agents can connect to its Agentic Commerce Protocol integration. The badge confirms discovery metadata; purchases are not tested.

Standards

llms.txt24A short guide to the site written for AI models: what it is and which pages matter most.
robots.txt33The file that tells crawlers where they may go. Every other rule a site gives to bots starts here.
Sitemap33A list of the site's pages, so a bot sees everything that exists instead of guessing from links.
Descriptive llms.txt16The llms.txt describes what is behind each link, so a model knows which pages are worth reading.
llms-full.txt or .md pages12The content is also available as plain Markdown, in one llms-full.txt file or as separate .md pages. Models can read it without the HTML.
Markdown negotiation3Pages come back as clean Markdown when a bot asks for it: just the content, without menus, styling and scripts.
AI crawler rules13The site says which AI bots may visit, for training, search or answering questions. Blocking some is fine; what counts is making a choice.
Content Signals3The site says how its content may be used: for search, in AI answers or to train AI. Any mix of yes and no counts.
schema.org JSON-LD24Structured data on the homepage says what the site is, such as a company, a product or an article, so machines don't have to guess.
Semantic HTML14The page has a clear structure: a main content area, headings in order, a header and a footer. A bot can tell the content from the rest.
Crawlable navigation24Observed homepage navigation exposes usable page addresses and section targets in HTML. Destinations are not fetched by this check.
Named links and buttons30Links and buttons in the collected homepage HTML have names recoverable from text, labels or native alternatives, including icon controls.
Named form fields10Observed homepage fields have recoverable names and recognizable input semantics. Submission behavior is not tested.
Control roles and states26Homepage controls meet static checks for roles, required states and relationship targets, using native HTML semantics where available.
Typed links3The page links to versions made for machines, such as a Markdown copy or an API description, so an agent can go straight to them.
Canonical URL31Each page names the one address that should be indexed and cited, so an agent quoting it links to the right URL.
Working section links13Links to part of a page, such as a table of contents or a skip link, lead to that section instead of the top of the page.

34 sites

AI & Machine Learning

Websites in the directory, with their Good for Bots score. Column headers sort the list.
Site	Category	Score
SkipBait skipbait.app AI YouTube video summarizer and chat extension for Chromium browsers	AI Products & Agents	View report for SkipBait:
Notify Sound notifysound.com Free customizable notification sounds with an AI editor and MCP server integration	Developer Tools & APIs	View report for Notify Sound:
Dark Harbor darkharbor.ai Digital employees for reception, lead follow-up, and administrative tasks	AI Products & Agents	View report for Dark Harbor:
StartupIdeasDB startupideasdb.com AI-powered startup research platform with validated market opportunities and business blueprints	AI Products & Agents	View report for StartupIdeasDB:
FeelPair feelpair.com AI-assisted live communication and mediation tool for couples experiencing conflict	AI Products & Agents	View report for FeelPair:
RemoveMate removemate.com Automated AI background removal for product photos, portraits and pets	AI Products & Agents	View report for RemoveMate:
Dropshipping desde cero dropshippingdesdecero.com Shopify themes, conversion audits, and tools for dropshippers by Alejandro Atienza	E-commerce Stores	View report for Dropshipping desde cero:
TheSaaSDir thesaasdir.com Curated directory of software and AI products with submission options	Directories & Aggregators	View report for TheSaaSDir:
XONER4 xoner4.github.io Public download and product information for the Honer AI Android application	AI Products & Agents	View report for XONER4:

Promarks a Pro listing, in gold. Pro never changes a score or a place in the order.What Pro includes