Semantica 🧠 — A framework for building semantic layers, context graphs, and decision intelligence systems with explainability and provenance.

VeritasGraph: Enterprise-Grade Graph RAG for Secure, On-Premise AI with Verifiable Attribution

A machine learning tool for fishing entities

The Map Everyone's Missing: LLM Knowledge Engineering in 2026 — First unified guide connecting RAG, Context Engineering, Harness Engineering, Skill Systems, Agent Memory, MCP, and Progressive Disclosure

Building and Using Knowledge Graphs made easy

CLIPS programs I have completed for Expert Systems (Rule-Based AI)

Practice #ontology engineering with Python (and other languages).

EMelodyGen creates emotional ABC melodies via templates. Rough4Q dataset is auto-labeled by small emotional datasets and music psychology to fine-tune backbone after augmentation with 99% correct rate, 91% emotional alignment and effective feature controls.|EMelodyGen通过模板控制ABC生成旋律情感。利用小型情感数据集和音乐心理学为Rough4Q数据集生成标签，经转换和增强后微调骨干网络。生成谱正确率99%，情感准确率为 91%。

Wikidata properties

The Knowledge Engineering ENvironment for Timeline-based Planning

This project aims to create an ontology for a university using the Protege editor. The ontology defines various classes and their relationships within the university domain. It also includes queries and rules implemented in Protégé and CLIPS to retrieve information from the ontology.

Transition from copy-pasting to Knowledge Engineering. A manifesto and toolkit for AI in Academia.

🖥 DBpedia Visualization and Knowledge Engineering (DBpedia可视化与知识工程)

This repository contains an ontology built using Protégé for modeling the domain of airfields, runways, taxiways, gates, and aircrafts. The ontology captures various constraints and relationships between different entities in the airfield domain.

Knowledge Engineering Course

The Medieval Manuscripts Ontology (MeMO, https://w3id.org/irnerio/ontology/memo) is an OWL 2 DL ontology that aims to provide a framework for the formal description of medieval codices and manuscripts.

Internship work done during Summer Internship'17 in Digital Media Lab, University of Bremen, Germany

Evaluation framework for LLM knowledge inputs — prompts, RAG corpora, skills, agent workflows. Fix the model, vary the artifact. Built-in statistical rigor: bootstrap CI, Krippendorff α, length-debias, saturation curves.

A planning-based agent capable of playing from only VGDL game descriptions.

Stanford Ontology 101 methodology for TypeScript domain modeling. 7-step process from competency questions to typed data architectures. Gruber 5 principles. 30+ concept mappings. Works with Claude Code, Cursor, Windsurf.