Our Story
US primary law as clean, structured data. Statutes, regulations, constitutions, court rules, and executive orders through a REST API, an MCP server, and a free open dataset, for developers and companies.
Built for developers and companies
US primary law is public, yet it is not usable. It lives across thousands of government sources, in inconsistent formats, with no stable structure and no single API. Any team that needs statutes or regulations inside its product has had to scrape, normalize, and maintain all of it alone. Vaquill AI was founded by a lawyer (Arshita) and an engineer (Priyansh) to fix that, turning US primary law into clean, structured, well-cited data that any developer can query.
Vaquill AI covers the complete US Code, the CFR, and all 52 state and territory statute codes: 4.9M+ sections of US primary law, normalized, cross-referenced, and citation-addressable. You reach it three ways, a REST API, an MCP server for AI agents, and Open US Law, a free open dataset published under CC BY 4.0. We provide the data and the tools to reach it, nothing else.
We serve developers and companies of every size, from small businesses to large enterprises: LegalTech and RegTech products, AI and ML teams, compliance and GRC platforms, universities, and government. The data is versioned, source-linked, and built to the reliability bar a production system needs, so what you ship stays grounded in real, verifiable primary law.
Join us as we build the data infrastructure for US primary law.
Meet Our Founders
The team building Vaquill AI, US primary law data infrastructure
Arshita Anand
Co-founder & CEO · Lawyer
Arshita is a lawyer who spent her early career inside the workflows that live and die on primary law: compliance checks, research under deadline, memos where one wrong citation sinks the whole argument. She came up through legal aid cells, moot courts, and clinical work, the side of the profession where you learn fast because no one else is going to clear the queue for you.
What she saw at every turn: the law everyone relies on is public, yet almost impossible to use as data. It is scattered across government sites, inconsistently formatted, and rarely addressable by citation. She started Vaquill AI to turn that public law into infrastructure the next generation of legal and compliance products can build on.
“Clean, well-cited primary law should be a solved problem. We are making US statutes and regulations something any team can query, instead of something everyone has to rebuild from scratch.”
Priyansh Khodiyar
Co-Founder & CTO · Engineer
Priyansh built and runs the data pipeline behind Vaquill AI: 4.9M+ sections of US primary law ingested, normalized, and made citation-addressable across the complete US Code, the CFR, and all 52 state and territory codes. He ships the REST API, the MCP server for AI agents, and Open US Law, the free open dataset, plus the verification checks that keep every section traceable to its official source.
He owns the reliability posture production teams grill on the first call: source-linked citations, versioned data, US data residency on AWS, AES-256 at rest, TLS 1.3 in transit. The stack is built for one question: can a developer trust that this section is exactly what the statute says?
Priyansh treats primary law as an accuracy and coverage problem first, a developer-experience problem second. The site, the docs, the REST API, the MCP server, and the open dataset all run on infrastructure he architected.