K

Knowledge Graph

Govern prompts, models, agents, evaluations, policies, and decisions with deterministic evidence, replayability and lineage.

The GitLab Knowledge Graph project aims to create a structured, queryable graph database from code repositories to power AI features and enhance developer productivity.

Documentation

Roadmap

ERA Ontology / “ERA Vocabulary” means a Technical Document issued by the Agency pursuant to Article 4(8) of Directive (EU) 2016/797, establishing human and machine readable data definitions and presentations and linked quality and accuracy requirements for each data element (ontology) of the rail system.

The Agency shall ensure the ERA vocabulary is maintained to reflect regulatory and technical developments affecting the rail system.’

Reference implementation for Reasonable Ontology Templates (OTTR)

ProductionMind is an open-source, graph-native manufacturing intelligence platform that connects every machine, process, and decision across the industrial ecosystem. Built with a modular architecture, it enables predictive maintenance, digital twins, supply chain intelligence, quality optimization, and AI-driven manufacturing workflows through a unified knowledge graph. ProductionMind provides an open foundation for building adaptive, intelligent, and transparent manufacturing systems. https://roxanneardary.com/productionmind/

CodexAtlas – A hybrid AI platform connecting the world’s legal systems. Builds a global legal knowledge graph with internal predictive reasoning and public-facing summaries. Adaptable to any jurisdiction, ethically excludes juvenile matters, and supports research, education, and government analysis. https://roxanneardary.com/codexatlas/

A Python ORM library for SPARQL.

ApolloCore is a self-contained, embeddable knowledge base that runs 100% locally with no external API dependencies. It combines vector search, keyword search, knowledge graphs, entity extraction, and LLM-powered query enhancement into a single high-performance C++23 library.

Axis Juris is a modular, open-source legal intelligence system designed to analyze and structure patent law, case law, and jurisdiction-specific regulations. It combines a continuously updating legal knowledge graph with AI-driven reasoning to provide sourced, cross-referenced analysis of statutes and precedents. Built for scalability across U.S. federal and state systems (and extendable internationally), Axis Juris focuses on legal alignment, conflict detection, and structured understanding of evolving law. https://roxanneardary.com/axisjuris/

Chainly is an open-source AI-powered data flow intelligence system that traces what happens to user data after login events across the web. It builds evidence-based graphs of how information moves between first-party services, third-party vendors, and data brokers, revealing real-world data sharing that is often hidden behind privacy policies. By combining network tracing, graph analysis, and AI-driven entity resolution, Chainly turns invisible post-login data propagation into a transparent, auditable system. https://roxanneardary.com/chainly/

Graph-based Live Anomaly Detection on Semantic Streams

A Go-based Open Source Universal Memory server that exposes a Model Context Protocol (MCP) interface for LLM clients. It provides semantic document search (for user documents), agent memory management, and a knowledge graph - backed by PgVector or ChromaDB - enabling AI agents to store, retrieve, and interconnect knowledge across sessions.

A linter for RDF.

A lightweight RDF parser which streams triples directly from/to disk or standard input/output.

Flexible GraphRAG: Python, LlamaIndex (LangChain also coming) Docker Compose: 8 Property Graph dbs, 3 RDF graph dbs, 10 Vector dbs, OpenSearch, Elasticsearch, Alfresco. 13 data sources (9 auto-sync), KG auto-building, RDF ontologies, schemas, LLMs, document processing, Docling, LlamaParse, GraphRAG, RAG only, Hybrid search, AI chat. React, Vue, Angular TypeScript frontends, FastAPI backend, REST API, MCP Server

ARSINOE SustainGraph (Knowledge Graph)

Materials and sample queries for the Practical Data Consumption Workshop at Rail Data Forum 2025.