@DanKornas: Adding a conversational interface to a website should not require rebuilding its content layer. NLWeb is a collection o…

X AI KOLs Timeline Tools

Summary

NLWeb is an open-source collection of protocols and Python tools that allows developers to add natural-language interfaces to websites without rebuilding the content layer, using existing Schema.org or RSS data.

Adding a conversational interface to a website should not require rebuilding its content layer. NLWeb is a collection of open protocols and Python tools for builders adding natural-language interfaces to websites. It helps you serve people and AI agents from the same endpoint by combining existing http://Schema.org or RSS data with a natural-language API that returns http://Schema.org JSON. Key features: • Natural-language protocol – exposes a core ask method for website questions. • Native MCP support – each NLWeb instance also acts as an MCP server. • Structured-data ingestion – works with site markup for products, recipes, attractions, reviews, and more. • Pluggable stack – supports multiple LLM providers and vector stores. • Builder toolkit – includes a query agent, REST API docs, UI widgets, demos, and setup guides. It’s open-source (MIT license). Note: The maintainers describe the implementation code as proof-of-concept examples, not a definitive solution. Link in the reply
Original Article
View Cached Full Text

Cached at: 07/28/26, 12:27 PM

Adding a conversational interface to a website should not require rebuilding its content layer.

NLWeb is a collection of open protocols and Python tools for builders adding natural-language interfaces to websites.

It helps you serve people and AI agents from the same endpoint by combining existing http://Schema.org or RSS data with a natural-language API that returns http://Schema.org JSON.

Key features: • Natural-language protocol – exposes a core ask method for website questions. • Native MCP support – each NLWeb instance also acts as an MCP server. • Structured-data ingestion – works with site markup for products, recipes, attractions, reviews, and more. • Pluggable stack – supports multiple LLM providers and vector stores. • Builder toolkit – includes a query agent, REST API docs, UI widgets, demos, and setup guides.

It’s open-source (MIT license).

Note: The maintainers describe the implementation code as proof-of-concept examples, not a definitive solution.

Link in the reply


Schema.org - Schema.org

Source: https://schema.org/ Note: You are viewing the development version ofSchema.org. Seehow we workfor more details.

Schema.orgis a collaborative, community activity with a mission to create, maintain, and promote schemas for structured data on the Internet, on web pages, in email messages, and beyond.

Schema.org vocabulary can be used with many different encodings, including RDFa, Microdata and JSON-LD. These vocabularies cover entities, relationships between entities and actions, and can easily be extended through a well-documented extension model. As of 2024, over 45 million web domains markup their web pages with over 450 billion Schema.org objects. Many applications from Google, Microsoft, Pinterest, Yandex and others already use these vocabularies to power rich, extensible experiences.

Founded by Google, Microsoft, Yahoo and Yandex, Schema.org vocabularies are developed by an opencommunityprocess, using the[email protected]mailing list and throughGitHub.

A shared vocabulary makes it easier for webmasters and developers to decide on a schema and get the maximum benefit for their efforts. It is in this spirit that the founders, together with the larger community have come together - to provide a shared collection of schemas.

We invite you toget started!

View our blog atblog.schema.orgor seerelease historyfor version 30.0.

Similar Articles