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

Leverages composable open-source SDKs (Senzing for entity resolution, spaCy/GLiNER for NER, LanceDB for vector storage, NetworkX for graph algorithms) rather than monolithic frameworks, enabling air-gapped local execution with optional remote LLM services. Implements a neurosymbolic AI pipeline that unbundles context engineering into discrete stages—entity resolution, ontology mapping, entity linking, and spectral indexing—with human-in-the-loop feedback integrated via Opik for MLOps observability and iterative optimization. Produces a GraphRAG-enhanced QA chatbot packaged as a Streamlit app with declarative LLM integration (DSPy) and interactive graph visualization.

214 stars. Available on PyPI.

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.