Open standards for verifiable legal reasoning.
Legal AI systems should not merely answer. They should cite, prove, replay, and explain. legalproof.dev develops the open schemas, conformance tests, and certification programs that let any legal AI system prove its work.
Any legal AI system can generate text. A LegalProof-compatible system must generate proof.
We do not own legal reasoning. We define how legal reasoning systems prove themselves — through a stable schema (ProofGraph), a thin-waist API, conformance tests, and a certification ladder vendors can adopt incrementally.
Six primitives. One auditable artifact.
ProofGraph schema
Claims, facts, authorities, defeaters, and conclusions as one auditable artifact.
Replay & attest
Versioned engine, knowledge graph, and rulebase, plus signed receipts.
Defeasible reasoning
Exceptions, overrides, rebuttals, and superior authority — modeled, not glossed over.
Status-at-time
Law-as-of-date is a first-class input, not an afterthought.
Conformance tests
Gold Proof Set, Temporal Drift, Jurisdiction Swap, Citation Replay.
Privacy by design
Redaction policies and signed digests. ZK-compatible roadmap.
Initial standards
Adopt incrementally. Certify what you ship.
Emits valid ProofGraph objects.
Authorities resolve to stable references.
Passes law-as-of-date tests.
Models exceptions and superior authority.
Output structured for review, not autonomous practice.
Replay, provenance, privacy, governance.