knowledge-graph-system
Active·★ 129·Apache-2.0·Updated 2026-10-02
Kappa Graph is a semantic knowledge graph system designed to extract concepts and relationships from various documents, providing an epistemic layer that measures the reliability and support of claims. It distinguishes itself by offering grounding scores, detecting contradictions, and preserving the full provenance chain to source evidence.
#Knowledge Graph#Semantic Search#Epistemic Metrics#Grounding Scores#Contradiction Detection#FUSE Filesystem#LLM Integration#Document Analysis
01
Features
01Ingest documents (PDFs, markdown, images, text)
02Search by meaning, not just keywords
03Check confidence with grounding scores and detect contradictions
04Trace claims and concepts back to original source evidence
05Query via AI assistants through MCP server integration
02
Compatibility
Python
Backend Runtime
Verified via docs
PostgreSQL
Database
Verified via docs
Apache AGE
Graph Database
Verified via docs
Ollama
LLM Inference
Verified via docs
FUSE
Filesystem Integration
Verified via docs
AI Assistants
Integration
Verified via docs
03
Quick start
1
$ git clone https://github.com/aaronsb/knowledge-graph-system.git
2
$ cd knowledge-graph-system
3
$ ./operator.sh init
4
$ ./operator.sh start
04
Use cases
↳Research synthesis and identifying disagreements across papers
↳Managing and querying complex technical documentation
↳Providing persistent, grounded memory for AI agents
↳Compliance and audit with full provenance chain tracking
05
Alternatives
project-synapse-mcp★ 11
Transforms raw text into interconnected knowledge graphs and autonomously generates insights through advanced pattern detection. It combines formal semantic analysis (Montague Grammar) with Zettelkasten methodology to create a true cognitive partnership with AI.
crg★ 76
Knowledge graph for token-efficient code reviews -- semantic search and call-graph resolution across your codebase.
kglite★ 73
Embedded Cypher knowledge graph for Python and Rust. Bundled MCP server, describe() schema, and code-graph parser for LLM agents.
ai-workshop★ 60
Building GenAI Apps in C#: AI Templates, GitHub Models, Azure OpenAI & More
Comments
Log in to leave a comment
No comments yet. Be the first!