Free Law Project / CourtListener
Free Law Project is a nonprofit that builds open legal tools, and CourtListener is its main platform. It gathers written opinions from federal and state courts, oral argument audio, citation networks, and financial disclosure filings for judges. The RECAP Archive, assembled from federal court records, adds hundreds of millions of docket entries and the documents attached to them.
You can pull data through a REST API, download bulk exports, or search the site directly. The bulk files make it straightforward to load a large slice of US case law into a retrieval pipeline without scraping page by page.
Most US court opinions are in the public domain, so the underlying text is free to reuse. You can read more about the organisation and its other projects at https://free.law.
Related sources
Cambridge Law Corpus
A research dataset of more than 250,000 UK court cases, mostly from the 21st century but with some reaching back to the 16th century. Built by the University of Cambridge for legal natural language processing work, it is available under restricted access for research use.
EDGAR (SEC Filings)
The US Securities and Exchange Commission's repository of corporate filings, including annual reports (10-K), quarterly reports (10-Q), current reports (8-K), and proxy statements. You can search the full text or pull filings in bulk through an API, which makes it a rich source for financial and regulatory RAG.
EUR-Lex
The official portal for European Union law. It provides EU treaties, legislation, case law, and legislative proposals in 24 languages, with bulk download available. A dependable source for multilingual legal and regulatory RAG across the EU.
Legislation.gov.uk
The official UK government legislation database, holding all UK Acts of Parliament and statutory instruments. It is available as XML and linked data, so you can load the full statute book into a RAG system rather than scraping individual pages.