LLM-Readable Docs
These docs are built to be read by agents as easily as by people. Every page has a markdown twin, and the whole corpus is published in the formats LLM tooling already looks for — so you can point Claude (or any agent) at DreamLake viz and have it answer accurately.
Fetch a single page
Append .md to any docs URL to get the raw markdown — no nav, no chrome:
Every page also advertises its markdown twin in the HTML head:
The whole site, two ways
/llms.txt— a short, linked index of every page (llmstxt.org standard). The entry point an agent reads first to decide what to fetch./llms-full.txt— every page concatenated into one markdown file. Drop the entire product into a context window in a single request.
These surfaces are the whole story for agents working on or with the
library — components, schema-viz, file-preview, integration into a host
app. Point the agent at llms.txt (or fetch the specific .md pages) and
it has everything these docs know.
For end users of DreamLake — visualizing a connected source, writing its
.dreamrc — there are installable task skills instead: see the
skills repo and the
source visualization guide.
Always current. The .md pages and both llms files are generated from
the same source on each deploy, so they can't drift from what you read on
the site — and the end-user skills lean on them for every detail instead of
carrying copies.