Directories & Aggregators

Browse directories and aggregators by AI visibility score. Review crawler access, listing descriptions and links that lead readers to the original source.

How websites are scored

Signals

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

Agent capabilities

API catalog1Lists 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.md0A 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 Auth0Publishes 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 commerce0Publishes how agents can connect to its Agentic Commerce Protocol integration. The badge confirms discovery metadata; purchases are not tested.

Standards

llms.txt4A short guide to the site written for AI models: what it is and which pages matter most.
robots.txt7The file that tells crawlers where they may go. Every other rule a site gives to bots starts here.
Sitemap7A list of the site's pages, so a bot sees everything that exists instead of guessing from links.
Descriptive llms.txt4The llms.txt describes what is behind each link, so a model knows which pages are worth reading.
llms-full.txt or .md pages2The 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 negotiation0Pages come back as clean Markdown when a bot asks for it: just the content, without menus, styling and scripts.
AI crawler rules3The site says which AI bots may visit, for training, search or answering questions. Blocking some is fine; what counts is making a choice.
Content Signals0The 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-LD7Structured 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 HTML4The 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 navigation7Observed homepage navigation exposes usable page addresses and section targets in HTML. Destinations are not fetched by this check.
Named links and buttons7Links and buttons in the collected homepage HTML have names recoverable from text, labels or native alternatives, including icon controls.
Named form fields4Observed homepage fields have recoverable names and recognizable input semantics. Submission behavior is not tested.
Control roles and states6Homepage controls meet static checks for roles, required states and relationship targets, using native HTML semantics where available.
Typed links0The 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 URL6Each page names the one address that should be indexed and cited, so an agent quoting it links to the right URL.
Working section links4Links 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.

Clear signals

Filters · 2 active

Signals

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

Agent capabilities

API catalog1Lists 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.md0A 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 Auth0Publishes 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 commerce0Publishes how agents can connect to its Agentic Commerce Protocol integration. The badge confirms discovery metadata; purchases are not tested.

Standards

llms.txt4A short guide to the site written for AI models: what it is and which pages matter most.
robots.txt7The file that tells crawlers where they may go. Every other rule a site gives to bots starts here.
Sitemap7A list of the site's pages, so a bot sees everything that exists instead of guessing from links.
Descriptive llms.txt4The llms.txt describes what is behind each link, so a model knows which pages are worth reading.
llms-full.txt or .md pages2The 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 negotiation0Pages come back as clean Markdown when a bot asks for it: just the content, without menus, styling and scripts.
AI crawler rules3The site says which AI bots may visit, for training, search or answering questions. Blocking some is fine; what counts is making a choice.
Content Signals0The 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-LD7Structured 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 HTML4The 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 navigation7Observed homepage navigation exposes usable page addresses and section targets in HTML. Destinations are not fetched by this check.
Named links and buttons7Links and buttons in the collected homepage HTML have names recoverable from text, labels or native alternatives, including icon controls.
Named form fields4Observed homepage fields have recoverable names and recognizable input semantics. Submission behavior is not tested.
Control roles and states6Homepage controls meet static checks for roles, required states and relationship targets, using native HTML semantics where available.
Typed links0The 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 URL6Each page names the one address that should be indexed and cited, so an agent quoting it links to the right URL.
Working section links4Links 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.

Clear signals

7 sites

schema.org JSON-LD

Websites in the directory, with their Good for Bots score. Column headers sort the list.
Site	Category	Score
SaaS Cubes saascubes.com Curated SaaS directory offering permanent do-follow backlinks for listed products	Directories & Aggregators	View report for SaaS Cubes:
Mydentify mydentify.com Weekly product leaderboard and directory for discovering indie software by job	Directories & Aggregators	View report for Mydentify:
RankCert rankcert.com Product launch board ranking items on verified domain control rather than upvotes	Directories & Aggregators	View report for RankCert:
StackLedge stackledge.com Curated directory of automation, AI and SaaS tools	Directories & Aggregators	View report for StackLedge:
ShipBoost shipboost.io Weekly launch boards and listings for bootstrapped SaaS founders	Directories & Aggregators	View report for ShipBoost:
OGList oglist.org Directory of nonprofits and government bodies working on human rights, transparency and the environment	Directories & Aggregators	View report for OGList:
Top Proxy top-proxy.com Catalog and comparison platform for mobile, residential, and server proxies	Directories & Aggregators	View report for Top Proxy:

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

Through a bot’s eyes

About Directories & Aggregators

A directory sits between a question and a source. It can help a reader find the right website, or add another layer of descriptions that all say the same thing. The useful version explains why an entry belongs, makes the original destination clear and lets readers narrow the collection without losing access to the listings.

That is the standard we aim to meet ourselves. Categories should describe a real distinction, listing pages should contain specific information, and navigation should work through ordinary links. An assistant should be able to tell what the directory observed and what came from the listed site's own claims.

A directory’s score applies only to its own website. Follow each listing to the original source for current features, terms and availability.

What to look for

Use these questions when reading the sites themselves. They are guidance for this category, not additional scoring checks.

Specific listing descriptions: Useful entries explain what differs between destinations. Repeating the same generic introduction across hundreds of pages gives a reader little to compare.
Navigation beyond search: Category links and reachable result pages provide a path through the collection. A search form alone can leave entries difficult to discover.
An unmistakable source link: The listing should identify the original site and make it easy to inspect. A directory summary is not a substitute for current provider information.
Placement explained: Readers should understand whether ordering reflects an observation, editorial selection or paid promotion. These are different reasons for an entry to appear first.

Frequently asked questions

Do you list other directories?

Yes. Directories and aggregators are a site type in this catalogue and use the same readability rubric as other sites.

Does a directory's score apply to its listings?

No. Each report describes the scanned website. A directory cannot pass its score on to the external sites it links to.

Can payment improve a Good for Bots score?

No. The score is never for sale. Paid plans and placements do not add points, hide a score or change the scoring rubric.

Questions about scores, scans and listings in general are answered in the FAQ.