benzsevern/goldenmatch

Entity resolution toolkit — deduplicate, match, and create golden records. 27 MCP tools on Smithery. Zero-config. 97.2% F1.

53
/ 100
Established

Uses Polars for columnar processing and combines RapidFuzz string similarity with FAISS vector search and sentence-transformers embeddings for hybrid matching. Includes Fellegi-Sunter probabilistic matching with EM-trained m/u probabilities, 8+ blocking strategies (including learned predicate selection), and optional LLM refinement; operates as Python library, REST API, or MCP server with Postgres sync, incremental matching, and privacy-preserving PPRL modes for cross-organization record linkage.

25 stars and 2,819 monthly downloads. Available on PyPI.

Maintenance 13 / 25
Adoption 15 / 25
Maturity 18 / 25
Community 7 / 25

How are scores calculated?

Stars

25

Forks

2

Language

Python

License

MIT

Last pushed

Mar 27, 2026

Monthly downloads

2,819

Commits (30d)

0

Dependencies

10

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/mcp/benzsevern/goldenmatch"

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