Use these docs with AI tools
Give an AI assistant these docs as Markdown, one page or the whole site.
Every page of this site is also served as Markdown, so an AI assistant can read it as plain text. Point your assistant at the page you are working from, or at the whole site.
One page
Each page has two buttons under its title:
- Copy Markdown copies the page as Markdown, ready to paste into a chat.
- Open shows the Markdown, or opens the page in ChatGPT, Claude, Cursor or Scira AI.
Any page's Markdown is also at its URL with .md added. For example, the
Quickstart is at https://sdk.nimbusprivacy.xyz/getting-started/quickstart.md.
The home page is at /index.md.
A request that asks for text/markdown in its Accept header is redirected to the page's .md
URL. Every page also names its Markdown copy in a Link header.
The whole site
These files describe the whole site:
| File | What it holds |
|---|---|
/llms.txt | An index: the package and its version, common tasks, then every page with a link to its Markdown and a one-line summary. |
/llms-full/<section>.txt | The full text of one section's pages. llms.txt names each section's file. |
/llms-full.txt | The full text of every page, in one Markdown file. |
Give your assistant llms.txt when it can fetch pages itself, and it reads only what it needs.
Give it one section's file when the task stays in that section. Give it llms-full.txt when it
cannot fetch, or when you want everything in one place.
Point an assistant at the docs
Add a line like this to your project's instructions for your assistant, such as AGENTS.md or
CLAUDE.md:
For @umbra-privacy/nimbus-solana-web, read https://sdk.nimbusprivacy.xyz/llms.txt first.
Fetch a page's Markdown by adding .md to its URL.The code on every page compiles against the SDK when the site is built. So an assistant that copies an example gets code that matched the SDK on that day.
Next
Last updated