Regulations.gov
Regulations.gov is the central portal for the US federal rulemaking process, run under the eRulemaking Program. It catalogues regulatory activity from hundreds of federal agencies, organised into dockets (folders that group a rulemaking together), documents (proposed rules, final rules, notices, and supporting or related material), and the public comments submitted in response. The collection is large: on the order of a million or more documents, several hundred thousand dockets, and tens of millions of public comments, growing continuously as agencies publish and the public responds.
Access is programmatic through the v4 REST API, hosted via api.data.gov, which returns JSON and is documented with an OpenAPI specification. A free API key registered at api.data.gov unlocks standard search and retrieval; a shared DEMO_KEY exists only for casual exploration. GET endpoints let you query and page through dockets, documents, and comments by agency, docket, document type, keyword, and date. Rate limits apply, so bulk harvesting of large comment sets takes planning and pagination. Community wrappers exist that download comments and documents for a docket into SQLite or CSV.
For RAG and AI, this is a strong source for regulatory question answering, policy analysis, and tracking public sentiment on federal rules. The text is well suited to chunking by document or comment, with docket and agency metadata as useful filters. Watch-outs: the corpus is raw and uneven, comments range from one line to lengthy attachments (often as linked PDFs rather than inline text), and duplicate or campaign comments are common. Federal agency works are public domain in the US, but public comments are third-party submissions that may contain personal data and copyrighted quotations, so the compilation licence does not extend cleanly to every item. If you need the published rules themselves in law-grade form, the Federal Register API is a close companion, and Data.gov catalogues the broader set of US open datasets.
Related sources
Companies House
The UK's official register of companies. Search every registered company, its directors, filing history, and accounts, or pull the data in bulk. A reliable source for UK corporate facts in a RAG system.
data.europa.eu
The European Data Portal, a single point of access to open data from 36 European countries and the EU institutions. Over 1.6 million datasets span every policy area, giving RAG systems broad, multilingual coverage of official European data.
data.gov
The US federal government's open data portal, gathering more than 300,000 datasets from federal agencies. Coverage spans agriculture, climate, education, energy, finance, health, and public safety, making it a broad source of official US data for RAG systems.
data.gov.uk
The UK Government's central catalogue of open public sector data, run by the Government Digital Service. More than 47,000 datasets cover health, housing, transport, demographics, and the environment, giving RAG systems a trusted base of UK facts, figures, and official records.