SFHAJJI/lex

**Point-in-time retrieval of regulatory text.** Regulators publish the current
rule; every audit, investigation and dispute is about a **past date**. Lex keeps
every version it has seen and answers *"what did this say on 15 March 2022?"*
with the exact validity interval, the timeline, the instrument that changed it,
and a hashed provenance record, and an honest, machine-readable refusal when it
cannot know.
**Live demo** ·
**Search held law** ·
**MCP endpoint** ·
**Dataset (CC-BY)** ·
**Examples** ·
**Architecture dossier** ·
**Benchmarks** ·
**Verify it yourself** ·
**Program** ·
**Retrieval + agent plan** ·
**Spec (D1-D82)** ·
**Corpus revalidation** ·
**Snapshot retention**
74-second engineering demo
*Dated retrieval → deterministic keyword or optional local hybrid search → exact
EU article → verified temporal diff → evidence export → deployed architecture.*
Watch the narrated, continuous-browser MP4
or read the release evidence.
Try it in 30 seconds
Give any MCP-capable AI the full toolset, no key, no install:
Modern clients such as VS Code and Cursor connect to the hosted endpoint directly:
For a client that only accepts local stdio servers, bridge to the same hosted
endpoint with a pinned version of the third-party mcp-remote adapter (Node.js 18+):
The hosted endpoint is canonical: no legal corpus, vector files or Azure
credentials are downloaded to the client. Lex also publishes its remote-server
metadata to the official MCP Registry from GitHub Actions using OIDC. Lex
intentionally does not publish an npm package: the command above is a
compatibility bridge for older clients, not a second implementation.
The following is a historical V2 example. The public assistant is temporarily
unavailable while Lex installs its deterministic V3 answer path; search, direct
law pages and MCP remain available. Historical answer, verbatim:
> **Q: What did CRR Article 92 require as capital ratios on 1 March 2020, and has that text changed since?**
>
> Quoted verbatim (Article 92(1)) from the CRR version in force on that date:
> *"Subject to Articles 93 and 94, institutions shall at all times satisfy the
> following own funds requirements: (a) a Common Equity Tier 1 capital ratio of
> 4,5 %; (b) a Tier 1 capital ratio of 6 %; (c) a total capital ratio of 8 %."*
>, eu-eurlex:32013r0575:2019-12-25 (valid 2019-12-25 → 2020-06-26),
> permalink.
>
> Article 92 has had **seven distinct texts**: 2013-06-26 → 2013-06-27,
> 2013-06-28 → 2019-12-24, 2019-12-25 → 2020-06-26, 2020-06-27 → 2021-06-28,
> 2021-06-29 → 2022-12-31, 2023-01-01 → 2024-12-31 and 2025-01-01 onward, each
> with its own permalink and sha256.
Every claim in that historical answer came from a deterministic tool call (the
trace was shown under each reply); the model did not answer from its own memory.
Do not take this file's word for it, the numbers above are checkable in one call,
and if they ever drift from the live system, that is a bug worth reporting:
Who uses this
- **A compliance officer** checking which text of an obligation was in force on
the date of the facts, with a permalink and a hash for the file.
- **A legal-tech developer** building RAG over law that must not hallucinate
versions: per-article chunks with valid_from/valid_to to filter *before*
similarity (dataset).
- **An external AI agent** using the public MCP tools directly. The site's own
assistant is unavailable during the V3 answer-path replacement.
- **A researcher** tracking how one article's text evolved across amendments
(article_history: every distinct text state, dated).
What it never does
Lex answers *what the rule was*. It does not decide "were we compliant?", "does
this apply to me?", or "what does this mean?", those are professional opinions.
The evidence, index and MCP layers never generate or interpret legal text
(fitness rule F10). The reviewed V3 assistant design may later explain retrieved