regulatory-data

This GitHub repository shows data collection and analysis for “Regulatory Fragmentation” paper by Kalmenovitz, Lowry and Volkova, The Journal of Finance (Forthcoming)

Public breach notification and regulatory record observatory

Read-only MCP server for the public SEC EDGAR API (filings, Form 4 insider trades, full-text search, 6 tools).

MCP server for Orbit Sentinel — space regulatory filings from FCC, ITU, UNOOSA, FAA-AST

Cigarspace — open-source knowledge platform for the global cigar market. Multi-source ingestion, customs data, hybrid pgvector + trigram search, FastAPI public API, React admin UI.

Automated pipeline for extracting drug safety information from FDA Structured Product Labels (SPL) using NLP and MedDRA mapping for pharmacovigilance research.

Regulation-to-ETF exposure mapping engine. Maps US federal regulations to industry sectors and ETFs using a 7-layer ontology.

Public API examples and provenance receipts for MORVS.

End-to-end model risk and liquidity stress research for U.S. banks using Call Reports: point-in-time data pipelines, quantile ML, challenger validation, reverse stress, recovery optimization, monitoring, and validation hardening.

Desktop archiver for public WeChat articles, plus standalone CLI collectors for selected SAMR, MIIT, and CATARC public sources.

Measuring and Modeling the US Regulatory Ecosystem

Dated signals from public national medicines registers. Reads Nigeria, Brazil and Tanzania, reports expired registrations, renewals falling due and active filers, with every claim traceable to a hashed snapshot.

Audrent's paid MCP server for U.S. Federal Register documents — search, retrieval, and watchlists for AI agents.

ETL pipeline unpivoting three years of Alberta Energy Regulator ST39 filings into a tidy fact table - 9 operators, 36 months, 251 monthly series. Surfaces Gibson Energy's +15.5% crude bitumen growth (2022-24) and synchronised spring turnarounds. Python to Power BI.

Free National Information Center — 1.5B rows of US banking regulatory data from 20 sources (1863-2026)

End-to-end FDA drug recall pipeline: ingests and validates enforcement report data (2013–2026), then compares administrative latency and backlog trends across Class I, II, and III severity tiers to test whether FDA's latency improvements were Class I-specific.

Curated, live-verified directory of open regulatory, sanctions, procurement, and compliance data sources - plus a working reference implementation covering 28 of them as pay-per-event Apify Actors, with Python/Node.js quickstart loaders and DevRel write-ups.

Agent-to-Agent (A2A) + Model Context Protocol (MCP) hub for peptides.

AI-powered platform that turns regulatory changes into a risk-prioritized implementation roadmap — mapping obligations to controls, apps, and business units. FastAPI + React.

Python library for checking chemicals against Japan's published risk assessment lists.