O'Reilly and Microsoft Launch Open Source NLWeb for AI App Development

May 20, 2025
O'Reilly has partnered with Microsoft to introduce NLWeb, an open-source platform designed to simplify AI app creation across the internet, as announced in a press release.
O'Reilly and Microsoft Launch Open Source NLWeb for AI App Development

O'Reilly Media has partnered with Microsoft Corporation to launch NLWeb, an open-source platform aimed at simplifying the creation of AI applications across the internet. Announced in a press release, NLWeb allows both human users and AI systems to perform complex, conversational searches without relying on centralized AI chat or search sites.

The integration of NLWeb into O'Reilly's platform will initially enable conversational search across 59,000 books, utilizing Schema.org metadata to ensure accurate results without the need for web crawling. This initiative aligns with O'Reilly's mission to connect diverse audiences with the knowledge they need.

Tim O'Reilly, founder and CEO of O'Reilly, emphasized the importance of NLWeb in maintaining the decentralized nature of the internet, allowing any site to offer conversational search capabilities similar to those found on platforms like ChatGPT and Google. Ramanathan Guha, Technical Fellow and CVP at Microsoft, praised the collaboration as a significant step towards integrating AI with the web.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like AI in Education or Daily AI Brief.

Also, consider following us on social media:

AI in Education AI Brief AI Brief (X)
Free newsletter

AI in Education

Weekly newsletter about AI in education. Covers AI-driven software for educators, schools, general innovations and regulatory updates.

AI Token Webinar

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more

You may also like

Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.