Main Page: Difference between revisions
Jump to navigation
Jump to search
Initial Main Page — project overview and navigation (via update-page on MediaWiki MCP Server) |
Fix navigation links: point to actual pages instead of categories (via update-page on MediaWiki MCP Server) |
||
| (3 intermediate revisions by the same user not shown) | |||
| Line 2: | Line 2: | ||
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. | 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. | ||
A jurisdiction-agnostic kernel, jurisdiction plugins (France and EU today, designed for any country), a robust ingestion pipeline, and services on top. The schema follows the OpenStreetMap model — six universal structural kinds, JSONB tags, zero schema migration to add a jurisdiction. | |||
Everything is published as '''Python libraries''' (MIT). The kernel, the corpus protocol, the jurisdiction drivers, the ingestion framework — all are composable packages that can be embedded in any application. Use the MCP server as-is, or import the libraries directly to build your own legal data product. | |||
Software licensed under '''MIT'''. Enriched data licensed under '''ODbL'''. | Software licensed under '''MIT'''. Enriched data licensed under '''ODbL'''. | ||
| Line 13: | Line 17: | ||
| [[Philosophy]] || Why Dura Lex exists — safety, transparency, sovereignty, professional secrecy | | [[Philosophy]] || Why Dura Lex exists — safety, transparency, sovereignty, professional secrecy | ||
|- | |- | ||
| [[Architecture]] || How the pieces fit together | | [[Architecture]] || How the pieces fit together — kernel, drivers, pipeline, services | ||
|- | |- | ||
| [[ | | [[Corpus]] || The data model — schema, tags, edges, quality, temporal versioning, FTS | ||
|- | |- | ||
| [[ | | [[Sources]] || Data dictionary — one page per ingest source, coverage matrix | ||
|- | |- | ||
| [[ | | [[Jurisdictions]] || Legal systems we cover and how they map to the unified schema | ||
|- | |- | ||
| [[ | | [[MCP]] || The public API — tools, safety guidelines, reference resolution | ||
|- | |- | ||
| [[ | | [[Development]] || For contributors — coding conventions, testing, packaging | ||
|- | |- | ||
| [[:Category:Design decisions|Design decisions]] || Architectural decision records | | [[:Category:Design decisions|Design decisions]] || Architectural decision records (coming soon) | ||
|} | |} | ||
== Current data == | == Current data == | ||
France is the first implementation. The architecture is designed for any jurisdiction. | |||
{| class="wikitable" | {| class="wikitable" | ||
|- | |- | ||
! Data !! Volume | ! Jurisdiction !! Data !! Volume | ||
|- | |||
| rowspan="7" | '''France''' || Court decisions || 3.4M | |||
|- | |||
| Legislation articles || 1.8M | |||
|- | |||
| Collective agreements || 299K articles + 382K enterprise agreements | |||
|- | |- | ||
| | | Administrative doctrine || 9.6K | ||
|- | |- | ||
| | | Companies || 24.2M | ||
|- | |- | ||
| | | Directors || 15M | ||
|- | |- | ||
| | | Cross-citations || 4.4M links | ||
|- | |- | ||
| | | rowspan="3" | '''EU''' || CJEU decisions || — | ||
|- | |- | ||
| | | ECHR decisions || — | ||
|- | |- | ||
| | | EU legislation (regulations, directives, decisions) || — | ||
|} | |} | ||
Latest revision as of 02:24, 23 April 2026
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.
A jurisdiction-agnostic kernel, jurisdiction plugins (France and EU today, designed for any country), a robust ingestion pipeline, and services on top. The schema follows the OpenStreetMap model — six universal structural kinds, JSONB tags, zero schema migration to add a jurisdiction.
Everything is published as Python libraries (MIT). The kernel, the corpus protocol, the jurisdiction drivers, the ingestion framework — all are composable packages that can be embedded in any application. Use the MCP server as-is, or import the libraries directly to build your own legal data product.
Software licensed under MIT. Enriched data licensed under ODbL.
Navigation
[edit | edit source]| Section | Description |
|---|---|
| Philosophy | Why Dura Lex exists — safety, transparency, sovereignty, professional secrecy |
| Architecture | How the pieces fit together — kernel, drivers, pipeline, services |
| Corpus | The data model — schema, tags, edges, quality, temporal versioning, FTS |
| Sources | Data dictionary — one page per ingest source, coverage matrix |
| Jurisdictions | Legal systems we cover and how they map to the unified schema |
| MCP | The public API — tools, safety guidelines, reference resolution |
| Development | For contributors — coding conventions, testing, packaging |
| Design decisions | Architectural decision records (coming soon) |
Current data
[edit | edit source]France is the first implementation. The architecture is designed for any jurisdiction.
| Jurisdiction | Data | Volume |
|---|---|---|
| France | Court decisions | 3.4M |
| Legislation articles | 1.8M | |
| Collective agreements | 299K articles + 382K enterprise agreements | |
| Administrative doctrine | 9.6K | |
| Companies | 24.2M | |
| Directors | 15M | |
| Cross-citations | 4.4M links | |
| EU | CJEU decisions | — |
| ECHR decisions | — | |
| EU legislation (regulations, directives, decisions) | — |