Main Page
Dura Lex is an open-source operating system for legal data.
It structures public legal data — legislation, case law, company registries, administrative guidance — into a jurisdiction-agnostic corpus, queryable by AI agents via MCP and by humans via a web portal.
Software licensed under MIT. Enriched data licensed under ODbL.
Navigation
| Section | Description |
|---|---|
| Philosophy | Why Dura Lex exists — safety, transparency, sovereignty, professional secrecy |
| Architecture | How the pieces fit together |
| Corpus | The data model — schema, tags, edges, quality, FTS |
| Sources | Data dictionary — one page per ingest source |
| Jurisdictions | Legal systems we cover |
| MCP | The public API — tools, guidelines, reference resolution |
| Development | For contributors — coding conventions, testing, packaging |
| Design decisions | Architectural decision records |
Current data
| Data | Volume | Sources |
|---|---|---|
| Court decisions | 3.4M | Judilibre, Conseil d'État, JADE, INCA, Cass, courts of appeal, CADA, CNIL, Constit |
| Legislation articles | 1.8M | LEGI (73 codes + non-codified laws) |
| Collective agreements | 299K articles + 382K enterprise agreements | KALI, ACCO |
| Administrative doctrine | 9.6K | BOFiP, CNIL |
| Companies | 24.2M | RNE/SIRENE |
| Directors | 15M | RNE |
| Cross-citations | 4.4M | Inter-document links |