Cito
Hybrid academic search over 236M papers, built for agents
102 followers
Hybrid academic search over 236M papers, built for agents
102 followers
Cito is a hybrid search engine over the Semantic Scholar corpus: 236M papers in the keyword index, 146M with SPECTER2 dense vectors, fused with RRF and reranked by a cross-encoder. Free web search with no signup, a plain JSON API, and a native MCP endpoint so agents like Claude Code can run deep literature research without upstream rate limits. Built because every academic API throttled my agents to death.
The sheer speed of this is impressive! I am not directly involved in academic research currently, but (like most people I guess) I have topics that I am curious to explore further. I spent a good while exploring the topics via this platform and was hugely impressed by the results, the UI and the speed with which they were returned. It was easy to access original content (where applicable) and I would certainly recommend.
Cito
@martin_tanner Thank you, this made my day. "Not a researcher but curious about topics" is honestly a use case I care about a lot, since most academic search assumes you already know the jargon. If you ever run into a topic where the results feel off or the path to the actual paper feels clunky, I would genuinely like to hear about it.