The agent-native web

Most of the web treats AI agents as intruders. We think the next decade of visitors will be people and their agents, so we built this site for both. Everything below is live on this domain today.

The principles

How this site works for agents

1. Every page has a machine twin

Every public data page carries a rel="alternate" link to its API equivalent: the catalog to /v1/catalog, a source page to its datasets endpoint, a series page to its observations. The { } control in the header opens the twin in one click.

2. Content negotiation

No agent should have to parse our HTML. Request any data page with Accept: application/json (or ?format=json) and it redirects straight to the structured answer.

3. A map for language models

/llms.txt is the site in one screen: what this is, where the docs are, where the API lives. /llms-full.txt is the complete documentation as a single markdown file, generated from the same source as the human docs.

4. Structured data

Every series page publishes schema.org Dataset markup with its license, temporal coverage, and CSV and JSON distributions. The catalog publishes DataCatalog.

5. MCP as a front door

The store speaks Model Context Protocol natively. Point any MCP client at https://starwell.dev/api/starwell/mcp and verified statistics become tools: search, observations, computed answers, deep analysis, monitors. An agent reads the same store this website reads.

6. Same rules for every visitor

Agents get the same rate limits and the same free keys as people. Every value cited on a page carries that citation in the API response too.

7. Public data only

The machine surfaces expose what the human pages expose. Accounts, keys, and usage stay behind authentication and out of every machine manifest.

On this site

Where to see it working

Adopt it

Make your site agent-native

None of this needs a framework:

If you adopt the pattern, or think it should say something it does not, write to hello@starwell.dev.