knowledge-engineering

VeritasGraph — open-source Knowledge Graph & GraphRAG framework on GitHub. Build multi-hop reasoning, ontology-aware retrieval, and verifiable attribution over your own data. Nodes, edges, RDF, linked-data — runs locally or in the cloud.

Building and Using Knowledge Graphs made easy

Reduce hallucinations through first-principles reasoning, verification, self-critique, and explicit uncertainty for AI agents.

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%。

Knowledge engineering for AI agents: distill corpora too big for any context window into small, verified, git-native knowledge bundles

John, an agent harness designed for building knowledge-dense applications.

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

MASEO: A Multi-Agent System for Explainable Ontology generation

CoLLM: Consistency of Large Language Models in Knowledge Engineering

A verifiable engineering knowledge engine that turns technical documents, CAD models, and equipment data into structured knowledge for humans and AI agents.

把一个职业冷启动成高保真、可执行的 SKILL.md —— S+D 两段式技能蒸馏(agent 出题→抽取→Gap Map→防杜撰 HITL)

UniGraph——一站式知识图谱智造平台，支持领域建模、文档知识抽取、图谱构建与可视化，以及可追溯的 GraphRAG 问答。

Hierarchical agent skills for domain ontology planning, research, construction, and validation with saved research artifacts and eval-ready workflows.

A Python library and CLI to convert SWRL rules between human-readable text and RDF, merge them into OWL ontologies, and extract rules back to text.

Enterprise AI Business Intelligence platform featuring semantic search, knowledge engine, persistent vector storage, and production-oriented architecture built with FastAPI, FAISS, and Python.

Governance layer for OKF knowledge bases — evidence-based verification, anti-patterns, and consumption priority for safety-critical domains.

This Repository contains all exercises done (in class and as assignments) during the course Knowledge Engineering and Business Intelligence at UNICAM LM-18 MS Computer Science

Meeting scheduler for groups of people in mobilities at different places. It includes the analysis of flights and lodging prices to return the better date and place for everyone to travel together.

A psychologically-grounded employee reflection agent built on a fully deterministic decision tree

ACM ICAIF 2025 FinDDR · FinCMini Agent (财小析) — 8-region financial report pipeline & rule library. Test Set rank #12.