Home

GoldenMatch Wiki

Find duplicate records in 30 seconds. No rules to write, no models to train.

pip install goldenmatch
goldenmatch dedupe customers.csv

Getting Started

Page	What you'll learn
Installation	pip install with optional extras
Quick Start	6 usage scenarios from zero-config to evaluation
Configuration	Full YAML config reference
CLI Reference	All 21+ CLI commands

Core Concepts

Page	What it covers
Pipeline Overview	Ingest, Block, Score, Cluster, Golden Records
Blocking Strategies	8+ strategies: static, adaptive, multi-pass, ANN, canopy, learned
Scoring	10+ scorers: exact, Jaro-Winkler, ensemble, embedding, probabilistic
Python API	import goldenmatch as gm — 101 exports

AI Integration

Page	What it does
MCP Server	30 tools for Claude Desktop, Claude Code, any MCP client
ER Agent (A2A)	10 skills for autonomous agent-to-agent workflows
LLM Boost	LLM scoring for borderline pairs ($0.04/dataset)

Advanced Features

Page	What it does
PPRL	Privacy-preserving record linkage (92.4% F1)
Domain Packs	7 built-in rulebooks (healthcare, finance, electronics, ...)
Streaming	Incremental / CDC record matching
Database Integration	Incremental Postgres sync with golden record versioning
GPU Routing & Vertex AI	Managed embeddings via Google Cloud
REST API	HTTP API for real-time matching
Interactive TUI	Gold-themed terminal UI with keyboard shortcuts
Evaluation	Precision/recall/F1 against ground truth

Reference

Page	Details
Benchmarks	97.2% DBLP-ACM, 72.2% Abt-Buy, 92.4% PPRL FEBRL4
Comparison	vs Splink, dedupe, RecordLinkage, Zingg
Architecture	Internal module structure

---

Part of the Golden Suite: GoldenCheck (validate) | GoldenFlow (transform) | GoldenMatch (deduplicate) | GoldenPipe (orchestrate)