Cito
Self-hosted academic search tool covering approximately 148 million papers, with semantic, hybrid, and keyword search.
About Cito
Cito is a self-hosted academic search tool built on the Semantic Scholar corpus, covering approximately 148 million papers and providing open-access links through OpenAlex. It supports semantic search using the SPECTER2 model, hybrid search, and keyword search; the page states that its search is not subject to the public API limit of one request per second. Users can deploy it in their own environment for paper discovery, literature research, and locating open-access versions, making it suitable for researchers and teams that need large-scale academic search.
Best for
Best use cases
Paper search and literature research
Finding open-access versions of papers
Building an academic search service in your own environment
Features
Large-scale academic corpus
Based on the Semantic Scholar corpus, covering approximately 148 million papers.
Multiple search modes
Supports semantic search (SPECTER2), hybrid search, and keyword search.
Open-access links
Enriched through OpenAlex to provide open-access links for papers.
Self-hosted deployment
Deploy academic search to run in your own environment.
Pros
- Self-hosted deployment in your own environment
- Covers approximately 148 million papers from the Semantic Scholar corpus
- Supports semantic (SPECTER2), hybrid, and keyword search
- The page states that search is not subject to the public API limit of one request per second