CanLII
CanLII is the free public library of Canadian law, run by the country's law societies. It covers the federal jurisdiction and every province and territory, hosting more than 300 databases of legislation and case law, and it does so in both English and French, which matters because much Canadian primary law is officially bilingual. On top of the raw judgments, its CanLII Connects feature adds thousands of case commentaries written by legal professionals, giving you interpretation and context alongside the decisions themselves.
Access is through the website, one document per page, with search and citation lookup. There is a CanLII API, but it is aimed at metadata and access is granted on request rather than open to all, and there is no general bulk download of the full corpus. In practice that means CanLII works best for targeted retrieval: fetching a specific decision or statute by citation and extracting its text, rather than mirroring everything into your own index.
The reason to respect that pattern is not just technical. CanLII's terms of use allow free reading but place clear restrictions on bulk reuse, scraping, and redistribution, so it is well suited to a retrieval system that pulls the documents it needs on demand and much less suited to wholesale harvesting into a commercial product. Read the terms before you build, and lean on citation-driven lookups rather than crawling.
For a Canadian legal RAG project, CanLII is the natural starting point and often the best single free window into the law of all its jurisdictions. It sits in the same family as BAILII for the UK and Ireland and AustLII for Australia: national legal information institutes that are generous about reading and cautious about bulk reuse. If you later need broad reuse rights, you will want to combine it with openly licensed government sources for the specific statutes and decisions you can obtain that way.
Related sources
AustLII
A free resource of medium-neutral case law and unreported judgments for all Australian jurisdictions, covering the whole country since 1995.
Awesome LegalTech
A curated list of legal technology resources: open-source platforms, AI models, companies, datasets, and tools spanning the global legal ecosystem. Useful for tracking new entrants in a fast-moving space.
BAILII (British and Irish Legal Information Institute)
Free access to British and Irish primary legal materials, covering UK and Ireland case law and legislation. Alongside the National Archives, one of the main free sources for reading UK judgments.
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.