ElevenLiy/MAKGED
MAKGED is the first multi-agent framework for collaborative error detection in knowledge graphs.
This framework helps data scientists and knowledge graph engineers ensure the accuracy of their knowledge graphs. It takes in existing knowledge graph data and identifies potential errors through a collaborative, explainable multi-agent system. The output is a clear indication of which connections or facts in the graph might be incorrect, making it easier for human experts to review and correct.
No commits in the last 6 months.
Use this if you manage large, complex knowledge graphs and need a reliable, transparent way to automatically detect errors and inconsistencies.
Not ideal if your data is not structured as a knowledge graph or if you only need simple rule-based error checks.
Stars
30
Forks
4
Language
Python
License
—
Category
Last pushed
Jul 20, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/ElevenLiy/MAKGED"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Plale-Lab/patra-knowledge-base
Knowledge Graph to capture AI/ML model lifecycle from creation through deployments.
KGCP/paper2lkg
A Local Knowledge Graph Construction (KGC) pipeline designed to transform individual academic...
SteveTANTAN/PoG
[WWW 2025] Paths-over-Graph: Knowledge Graph Empowered Large Language Model Reasoning
brandburner/fabula
Turn television drama into storyworld knowledge graphs
zjunlp/xKG
Executable Knowledge Graphs for Replicating AI Research