Local-first, with byte-level provenance on every edge. Deterministic by default — the same corpus always yields a byte-identical graph you can audit and re-verify — with opt-in LLM extraction, grounded answer synthesis, and semantic search layered on top, always quarantined so model output never poses as ground truth.
pip install textgraph-kg
Each edge carries a re-verifiable
[doc:byte-span] citation — re-hash it against the source and it still matches.
WHY/DECISION/ADR markers become a queryable causal chain; export a W3C PROV-O audit trail.
Contradictory single-truth claims are surfaced for review, resolved only on an explicit, non-destructive policy.
Optional GQL, vision retrieval, access control, and Graph-of-Thoughts reasoning — each an opt-in module.