OneCite - Universal Citation & Academic Reference Toolkit๏
OneCite is a powerful command-line tool and Python library designed to automate the tedious process of citation management. Feed it anythingโDOIs, paper titles, arXiv IDs, or even a mixโand get clean, accurate bibliographic entries in return.
Getting Started
User Guides
- Advanced Usage
- Interactive Disambiguation
- Batch Processing Multiple Files
- Working with Different Data Sources
- Custom Templates
- Working with Large Reference Lists
- Error Handling and Recovery
- Converting Between Formats
- Using with Git for Version Control
- Integration with LaTeX and Overleaf
- Python API Advanced Usage
- Next Steps
- Python API Reference
- AI Assistant Integration with MCP
- Custom Templates
- Output Formats
API Reference
Key Features๏
๐ Smart Recognition - Fuzzy matching against multiple academic databases
๐ Universal Formats - Support for BibTeX, APA, and MLA output formats
๐ฏ High-Accuracy Pipeline - 4-stage process ensures highest quality output
๐ค Auto-Completion - Automatically enriches entries with missing metadata
๐ 7+ Citation Types - Handles journal articles, conference papers, books, software, datasets, theses, and preprints
๐ Universal Identifiers - Accepts DOI, PMID, arXiv ID, ISBN, GitHub URLs, Zenodo DOI, or plain text queries
๐ค AI Assistant Integration - Full Model Context Protocol (MCP) support
Data Sources๏
OneCite integrates with multiple authoritative academic data sources:
CrossRef - Academic publication metadata
Semantic Scholar - AI-powered literature search
OpenAlex - Open academic graph
PubMed - Biomedical literature
DBLP - Computer science bibliography
arXiv - Preprint repository
DataCite - Scientific datasets
Zenodo - Open research data
Google Books - Book metadata
Quick Start๏
Installation:
pip install onecite
Create a references.txt
file:
10.1038/nature14539
Attention is all you need, Vaswani et al., NIPS 2017
Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. MIT Press.
Run OneCite:
onecite process references.txt -o results.bib --quiet
For more information, see Quick Start Guide.