Documentation

Context Graph

A decision-aware knowledge-graph system built on LightRAG. It extends triples (h, r, t) into contextual quadruples (h, r, t, rc) — attaching the decision record (who, why, when, under which policy) to every edge — and adds CGR3 reasoning, a business rules engine, a typed ontology, web ingestion, and a governed action layer.

(h, r, t, rc) quadruples CGR3 reasoning rules & ontology web ingester MCP + REST multi-tenant
Start here

Read these first

The idea in narrative form, and the complete technical reference.

Feature guides

The productisation layer

Governance, ingestion, and execution — each with its own illustrated walkthrough.

Use cases

What to point it at

The whole stack, aimed at a concrete problem. AI-driven software development is the first.

Deep dives & reference

Design, architecture, operations

The build log and the long-form reference docs. Markdown files open on GitHub.

Getting started
Set USE_CONTEXT_GRAPH=true, start lightrag-server (port 9621), and open the WebUI — the Rules and Ontology tabs manage governance, POST /scrape pulls a website into the graph, and POST /actions/invoke runs governed operations. Full setup lives in the README.