pip install name-variants

from name_variants import lookup, share_cluster

clusters = lookup("Chan")
# [NameCluster(language='chinese', 8 forms),
#  NameCluster(language='korean_given', 3 forms)]

# Both Chinese scripts are in the same cluster — co-equal
assert "陳" in clusters[0]   # Traditional
assert "陈" in clusters[0]   # Simplified

# Membership is case-insensitive
assert "CHAN" in clusters[0]

# Ambiguity is surfaced, not suppressed
assert len(clusters) == 2    # Chinese AND Korean, not one-or-the-other

from name_variants import lookup

lookup("Chan")
# [NameCluster(language='chinese', 8 forms),
#  NameCluster(language='korean_given', 3 forms)]

lookup("Nguyen")
# [NameCluster(language='vietnamese', 4 forms)]

lookup("Smith")
# []

from name_variants import share_cluster

share_cluster("Chan", "Chen")        # True  — same Chinese cluster
share_cluster("Chou", "Zhou")        # True  — Wade-Giles = Pinyin
share_cluster("Chiang", "Jiang")     # True  — Chiang Kai-shek / 蒋介石
share_cluster("Hsu", "Xu")           # True  — Taiwan diaspora romanization
share_cluster("Tsao", "Cao")         # True  — Ts'ao Ts'ao / 曹操
share_cluster("Chan", "Kim")         # False — different names
share_cluster("", "Chan")            # False — empty input

from name_variants import dialect

dialect("chen")   # "mandarin_pinyin"
dialect("chan")   # "cantonese"
dialect("tan")    # "hokkien"
dialect("陳")     # "traditional"

dialect("chou")   # "wade_giles"
dialect("hsu")    # "wade_giles"
dialect("Smith")  # None

from name_variants import normalize

normalize("  NGUYỄN  ")                    # "nguyễn"
normalize("Nguyễn", strip_diacritics=True) # "nguyen"
normalize("chan​")                          # strips zero-width spaces

nv lookup Chan
# [chinese] (~90M bearers)
#   陳  陈  chan  chen  tan  ...
# [korean_given]
#   찬  chan  chahn

nv match Chan Chen          # true
nv match Chan Kim           # false
nv match --exit-code Chan Chen && echo same   # shell-scripting friendly

nv canonicalize-csv names.csv --col name --out out.csv
# adds {name}_canonical column

nv dedupe names.csv --col name --out out.csv
# adds cluster_id column grouping romanization variants

pip install "name-variants[pandas]"

import pandas as pd
import name_variants  # registers .nv accessor

s = pd.Series(["Chan", "Chen", "Smith", "Park"])

s.nv.lookup()
# 0    [NameCluster(chinese, ...), NameCluster(korean_given, ...)]
# 1    [NameCluster(chinese, ...)]
# 2    []
# 3    [NameCluster(korean, ...)]

s.nv.cluster_id()
# 0    a3f2b1c4d5e6   ← same as row 1 (Chan and Chen share chinese cluster)
# 1    a3f2b1c4d5e6
# 2                   ← empty string for unknown
# 3    9b8c7d6e5f4a

a = pd.Series(["Chan", "Park"])
b = pd.Series(["Chen", "Bak"])
a.nv.share_cluster_with(b)   # [True, True]

claude mcp add name-variants -- uvx --from "name-variants[mcp]" nv-mcp

{
  "mcpServers": {
    "name-variants": {
      "command": "uvx",
      "args": ["--from", "name-variants[mcp]", "nv-mcp"]
    }
  }
}

from name_variants import ALL_TABLES
list(ALL_TABLES.keys())   # all 18 table names

@dataclass(frozen=True)
class NameCluster:
    forms: frozenset[str]    # all representations — co-equal
    language: str            # "chinese", "korean", "vietnamese", etc.
    frequency: int | None    # approximate global bearer count

    def __contains__(self, text: str) -> bool  # case-insensitive
    def __iter__(self)                          # iterate all forms
    def __len__(self)

git clone https://github.com/SecurityRonin/name-variants
cd name-variants
pip install -e ".[dev]"
pytest

"陈": {
    "forms": ["陳", "chen", "chan", "tan", ...],
    "frequency": 90_000_000,
    "dialects": {
        "chen": "mandarin_pinyin",
        "chan": "cantonese",
        "tan":  "hokkien",
        "陳":   "traditional",
    },
},