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.

Hi Product Hunt! I built Cito because I kept hitting rate limits while doing literature research with AI agents. Google Scholar has no API at all, and Semantic Scholar's defaults to 1 request per second. Fine for a human, but an agent doing a deep-research run fires dozens of queries and just stalls. So I indexed the corpus myself: 236M papers, hybrid BM25 + SPECTER2 dense retrieval fused with RRF, reranked by a cross-encoder, served from a single CPU box in under half a second. What makes it different: - Web search works with no signup - Plain JSON API with honest, generous limits (free keys: 100 req/min, vs 1 req/sec upstream) - Native MCP endpoint: one command and Claude Code / Cursor can search the literature directly It is deliberately a retrieval engine, not a chatbot. It returns ranked papers with abstracts, citation counts, open-access PDF links and DOIs; the reasoning layer is your agent's job. Would love feedback, especially from anyone building research agents. If a rate limit ever blocks legitimate work, tell me and I will raise it.

The MCP endpoint is what sold me. I keep hitting the Semantic Scholar 1 req/sec wall when Claude runs a deep lit-research pass and it just stalls. Does the free 100/min hold up for a full run, or does it throttle once an agent goes wide?

Cito

Hybrid academic search over 236M papers, built for agents

Hybrid academic search over 236M papers, built for agents