ER Agent

pip install goldenmatch[agent]
goldenmatch agent-serve --port 8200

GET http://localhost:8200/.well-known/agent.json

{
  "mcpServers": {
    "goldenmatch": {
      "command": "goldenmatch",
      "args": ["mcp-serve", "--file", "customers.csv"]
    }
  }
}

{
  "results": {
    "clusters": 42,
    "match_rate": "8.4%"
  },
  "reasoning": {
    "domain_detected": "people",
    "strategy_chosen": "exact_then_fuzzy",
    "why": "Email has 92% uniqueness -- strong exact key. Name has spelling variation -- jaro_winkler at 0.85.",
    "alternatives_considered": [
      {"strategy": "pprl", "why_not": "No sensitive fields detected."},
      {"strategy": "fellegi_sunter", "why_not": "Fuzzy gives better recall for this data."}
    ],
    "confidence_distribution": {
      "auto_merged": 38,
      "review_queue": 4,
      "auto_rejected": 0
    }
  },
  "storage": "memory"
}

from goldenmatch import AgentSession

session = AgentSession()
result = session.deduplicate("customers.csv")

# Check what needs review
pending = session.review_queue.list_pending("customers")
for item in pending:
    print(f"Pair ({item.id_a}, {item.id_b}): score={item.score}")
    print(f"  Explanation: {item.explanation}")

# Approve or reject
session.review_queue.approve("customers", 0, 1, decided_by="human")
session.review_queue.reject("customers", 2, 3, decided_by="human", reason="Different entities")

# Stats
print(session.review_queue.stats("customers"))
# {"pending": 2, "approved": 1, "rejected": 1}

from goldenmatch import AgentSession

session = AgentSession()

# Analyze data and get strategy recommendation
analysis = session.analyze("customers.csv")
print(analysis["strategy"])  # "exact_then_fuzzy"
print(analysis["why"])

# Deduplicate with full reasoning
result = session.deduplicate("customers.csv")
print(result["results"]["clusters"])
print(result["reasoning"]["why"])

# Compare strategies
comparison = session.compare_strategies("customers.csv")
for strategy, metrics in comparison.items():
    print(f"{strategy}: {metrics['clusters']} clusters, {metrics['match_rate']:.1%} match rate")

# Match two sources
matches = session.match_sources("new_customers.csv", "master.csv")

# v1.7-v1.12: explicit AutoConfigController invocation
autoconf = session.autoconfigure("customers.csv")
print(autoconf["telemetry"]["stop_reason"])     # e.g. "green"
print(autoconf["telemetry"]["health"])          # e.g. "green"
for decision in autoconf["telemetry"]["decisions"]:
    print(f"iter {decision['iteration']}: {decision['rule_name']}")

# Telemetry is also cached on `deduplicate` / `match_sources` calls
session.deduplicate("customers.csv")
print(session.last_telemetry)                    # same shape as autoconfigure's telemetry

{
  "name": "GoldenMatch ER Agent",
  "description": "Autonomous entity resolution agent for deduplication, matching, and data quality.",
  "url": "http://localhost:8200",
  "version": "1.26.0",
  "provider": {
    "organization": "GoldenMatch",
    "url": "https://github.com/benseverndev-oss/goldenmatch"
  },
  "capabilities": {
    "streaming": false,
    "pushNotifications": false
  },
  "skills": [
    {
      "id": "deduplicate",
      "name": "Deduplicate",
      "description": "Run deduplication pipeline on a single file.",
      "inputModes": ["application/json"],
      "outputModes": ["application/json"]
    }
  ],
  "authentication": {
    "schemes": ["bearer"]
  }
}

export GOLDENMATCH_AGENT_TOKEN="your-secret-token"
goldenmatch agent-serve --port 8200