GitHub - CKL75/semantic-manifest-specification: An open data standard and streamable content graph specification (NDJSON) designed to optimize website discovery, content relations, and text ingestion for AI crawlers, LLMs, and RAG engines. · GitHub
/" data-turbo-transient="true" />
Skip to content
Search or jump to...
Search code, repositories, users, issues, pull requests...
-->
Search
Clear
Search syntax tips
Provide feedback
--><br>We read every piece of feedback, and take your input very seriously.
Include my email address so I can be contacted
Cancel
Submit feedback
Saved searches
Use saved searches to filter your results more quickly
-->
Name
Query
To see all available qualifiers, see our documentation.
Cancel
Create saved search
Sign in
/;ref_cta:Sign up;ref_loc:header logged out"}"<br>Sign up
Appearance settings
Resetting focus
You signed in with another tab or window. Reload to refresh your session.<br>You signed out in another tab or window. Reload to refresh your session.<br>You switched accounts on another tab or window. Reload to refresh your session.
Dismiss alert
{{ message }}
CKL75
semantic-manifest-specification
Public
Notifications<br>You must be signed in to change notification settings
Fork
Star
main
BranchesTags
Go to file
CodeOpen more actions menu
Folders and files<br>NameNameLast commit message<br>Last commit date<br>Latest commit
History<br>2 Commits<br>2 Commits
LICENSE.md
LICENSE.md
README.md
README.md
semantic-manifest-specification.md
semantic-manifest-specification.md
semantic-manifest.jsonl
semantic-manifest.jsonl
View all files
Repository files navigation
The Semantic Manifest Specification
An open data standard and streamable content graph specification (NDJSON) designed to optimize website discovery, content relations, and text ingestion for AI crawlers, LLMs, and RAG engines.
The Problem
Traditional web standards are fundamentally broken for AI search engines at scale.
Sitemaps pass raw URLs without structural context.
JSON-LD is trapped in single-page scopes.
llms.txt files are flat text that consume massive amounts of context window tokens when scaling to thousands of pages.
The Solution
The Semantic Manifest bridges this gap. It uses a streamable NDJSON format so AI crawlers can parse an entire site's content types, relational entities, and explicitly designated "markdown twins" line-by-line efficiently.
System Performance Demo
Within hours of launching a ~58,000-page site with a Semantic Manifest linked in the , ClaudeBot ingested the entire site at ~7 URLs per second.
📺 Watch the System Performance & Crawl Log Demo Video Here
Core Documentation
📖 Read the Full Specification (v0.1)
📄 View the Reference JSONL
Reference Implementations
This standard is a native, built-in structural component of the High-Velocity Content Engine (HVCE).
Live production manifests can be viewed at:
EduStats (58,000 pages): edustats.app/semantic-manifest.jsonl.
Hypersonic SEO Framework: hypersonicseo.com/semantic-manifest.jsonl
License & Authorship
Semantic Manifest Specification (v0.1) © 2026 by Chris Limner / Hypersonic SEO.<br>This work is marked with CC0 1.0 Universal.
About
An open data standard and streamable content graph specification (NDJSON) designed to optimize website discovery, content relations, and text ingestion for AI crawlers, LLMs, and RAG engines.
Resources
Readme
License
View license
Uh oh!
There was an error while loading. Please reload this page.
Activity
Stars
stars
Watchers
watching
Forks
forks
Report repository
Releases
No releases published
Packages
Uh oh!
There was an error while loading. Please reload this page.
Contributors
Uh oh!
There was an error while loading. Please reload this page.
You can’t perform that action at this time.