TABLE · NO INSTALL
dedupe entities
Find records in a supplier/customer/store list that are probably the SAME entity under different names — "北京星辰科技有限公司" vs "星辰科技(北京)" — by cross-checking name similarity against hard identifiers: tax ID (统一社会信用代码, checksum-verified), phone, domain, bank account, address. It never merges anything: it returns candidate groups with the evidence for each link, pairs that need human review, and — just as important — pairs that LOOK alike but are provably different entities (different valid tax IDs), because wrongly merging two real companies is the expensive mistake. One URL. No install, no API key, free during the beta.
Try it right here
No install, no key, no signup — this runs the same endpoint an agent calls. Free during the beta, subject to fair capacity limits.
Call it
curl "https://ainetcafe.com/t/dedupe_entities?...params"Response contains a hosted file URL. All calls are temporarily free during the beta; fair capacity limits apply.
Also callable via MCP and the Python SDK.
Same family
clean_table — Tidy a messy CSV: drop duplicate rows, trim whitespace, unify blank values, remove empty rows/columns, split one column into several, transpose rows/columns, or reshape a wide table into a long one (the format analysis tools want)
merge_tables — Merge several CSVs into one
match_transactions — Match bank statement lines to ledger/invoice entries when there is NO shared key — by amount, date window, reference numbers found inside free-text descriptions, and fuzzy counterparty names ("北京XX科技" vs "XX科技(北京)")
read_xlsx — Read an Excel
write_xlsx — Build an Excel
reconcile_ledger — Reconcile two ledgers (e
diff_tables — Compare two tables row by row on a key column and report what differs — rows only in A, only in B, and rows present in both whose other columns disagree (with the exact column and both values)
merge_tables — Merge several CSVs into one
match_transactions — Match bank statement lines to ledger/invoice entries when there is NO shared key — by amount, date window, reference numbers found inside free-text descriptions, and fuzzy counterparty names ("北京XX科技" vs "XX科技(北京)")
read_xlsx — Read an Excel
write_xlsx — Build an Excel
reconcile_ledger — Reconcile two ledgers (e
diff_tables — Compare two tables row by row on a key column and report what differs — rows only in A, only in B, and rows present in both whose other columns disagree (with the exact column and both values)