
Connected Papers: Data Source and How Graphs Are Built
Connected Papers builds similarity graphs of research papers from the Semantic Scholar corpus. How the graph works and how papers get in.
AI SEARCH ENGINES
Comprehensive guides to AI-powered search engines and how they discover, crawl, and surface your content.

Connected Papers builds similarity graphs of research papers from the Semantic Scholar corpus. How the graph works and how papers get in.

Consensus searches over 200 million research papers from Semantic Scholar, OpenAlex and its own crawl. How its search and ranking work.

Coveo is search software that companies run on their own sites. How its crawler Coveobot handles robots.txt, noindex and crawl rate.

DeepSeek runs its own search engine for its chat app and its Search and Fetch APIs. What is documented, and what site owners can control.

Duck.ai gives anonymous access to third-party AI models. How Search Assist answers cite pages, and which DuckDuckGo crawlers to allow.

Elasticsearch is search software you run yourself or on Elastic Cloud. Its semantic search options and the Elastic Open Crawler user agent.

Elicit searches about 138 million papers from Semantic Scholar, OpenAlex and PubMed. Its sources, search method and web access.

Exa is a web search API for AI apps. Its crawler ExaSearchBot follows robots.txt and signs requests. User agents, opt-out and removal.

Felo is a multilingual AI search engine from Felo Inc. It answers from real-time web results with citations. No crawler is documented.