DerwenAI/strwythura

Strwythura: construct an entity-resolved knowledge graph from structured data sources and unstructured content sources, implementing an ontology pipeline, plus context engineering for optimizing AI application outcomes within a specific domain. This produces a Streamlit app, with MLOps instrumentation.

60
/ 100
Established

This project helps data professionals build a specialized knowledge graph from diverse information, including spreadsheets and research papers. It takes structured data and unstructured text to produce a comprehensive, domain-specific knowledge graph enriched with entity relationships. Data scientists, machine learning engineers, and MLOps teams can use this to create robust context for AI applications.

214 stars. Available on PyPI.

Use this if you need to combine various data sources into a structured knowledge base to improve the accuracy and relevance of your AI models or chatbots in a specific field.

Not ideal if you're looking for an out-of-the-box, general-purpose AI solution without needing to understand or customize the underlying knowledge graph construction.

knowledge-graph-construction natural-language-processing information-extraction AI-context-engineering data-integration
Maintenance 10 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 15 / 25

How are scores calculated?

Stars

214

Forks

23

Language

Python

License

MIT

Last pushed

Feb 03, 2026

Commits (30d)

0

Dependencies

37

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/DerwenAI/strwythura"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.