mykg
Active·★ 77·MIT·Updated 2026-10-08
myKG automatically generates confidence-scored knowledge graphs from diverse document types, grounded in an induced RDFS/OWL ontology. It builds trustworthy knowledge graphs through a self-evolving ontology that adapts, maintains consistency, and assigns confidence scores to extracted knowledge.
#Knowledge Graph#LLM#Ontology#Document Processing#Graph Extraction#AI Assistant#RAG#Data Extraction
01
Features
01Schema-guided knowledge graph generation grounded in a formal RDFS/OWL schema.
02Supports mixed-format corpora including PDF, Word, HTML, and images, automatically converted to Markdown.
03Provides five output formats: JSONL, Turtle RDF, NetworkX, Obsidian vault, and Neo4j LOAD CSV.
04Enables incremental updates and schema growth by appending new or modified files to existing sessions.
05Integrates with AI coding assistants (e.g., Claude Code) by exporting an Obsidian vault as a 'second brain' for context.
02
Compatibility
Python
Runtime
Verified via docs
Python 3.11+
Version
Verified via docs
Anthropic
LLM Provider
Verified via docs
OpenAI
LLM Provider
Verified via docs
Ollama
Local LLM
Verified via docs
OpenRouter
LLM Provider
Verified via docs
03
Quick start
1
$ pip install mykg
2
$ mykg init
04
Use cases
↳Converting websites, GitHub repositories, and personal notes into queryable knowledge graphs.
↳Building a 'second brain' for AI coding assistants to ground answers and trace relationships in documents.
↳Creating an LLM-powered wiki from diverse documents for AI agents to reason over.
↳Facilitating human-in-the-loop ontology design and refinement through schema review gates.
05
Alternatives
flexible-graphrag★ 194
Flexible GraphRAG: Python, LlamaIndex, Docker Compose: 8 Graph dbs, 10 Vector dbs, OpenSearch, Elasticsearch, Alfresco. 13 data sources (9 auto-sync), KG auto-building, schemas, LLMs, Docling or LlamaParse doc processing, GraphRAG, RAG only, Hybrid search, AI chat. React, Vue, Angular frontends, FastAPI backend, REST API, MCP Server. Please 🌟 Star
sparql-llm★ 130
🦜✨ Chat system, MCP server, and reusable components to improve LLMs capabilities when generating SPARQL queries
solon-ai★ 466
Java AI application development framework (supports LLM-tool,skill; RAG; MCP; Agent-ReAct,Team-Agent). Compatible with java8 ~ java25. It can also be embedded in SpringBoot, jFinal, Vert.x, Quarkus, and other frameworks.
rosetta★ 50
MCP Server with RouterOS docs + commands + products + changelogs, using SQLite-as-RAG, sourced from MikroTik
ragflow★ 92.6k
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
Comments
Log in to leave a comment
No comments yet. Be the first!