Entify

5.6easy start · #106 of 109
in AI Presentation Makers

Runs on api, self-hosted, Web.

Entify is ranked #106 of 109 in AI presentation makers on The Geeks Club. It runs on API, Self-hosted, Web.

Compared on AI presentation makers

Decks.Studio 0 of 4 in the starter kit Lesson 18.8 Pitch 0 of 4 in the starter kit Lesson 28.7 OpenCharts 0 of 4 in the starter kit Lesson 38.6 ChatSlide 0 of 4 in the starter kit Lesson 48.6 arg.ai 0 of 4 in the starter kit Lesson 58.6 Gamma 0 of 4 in the starter kit Lesson 68.3

Purpose: Entify is an open-source workspace for resolving entities, linking records, and deduplicating messy datasets.
Matching engine: It uses Splink 4 and DuckDB to match records and review explainable clusters.
Automatic setup: Its auto-configuration identifies likely column types, proposes blocking rules, and explains decisions that users can override.
Data formats: It reads CSV, TSV, Parquet, JSON, and Excel files.
Review and export: Users can inspect match evidence and threshold analyses, export deduplicated data, and generate a PDF audit report.
Integrations: Optional sign-in and shared storage use Clerk authentication and Supabase persistence; demo mode works without them.
Local operation: The README says the Docker quickstart needs no accounts, API keys, or external services, and uploaded data stays on the machine.
Optional semantic blocking: Semantic blocking is optional and requires an additional install that downloads roughly 600 MB of Torch dependencies.
Limits: Uploads have a 100 MB cap, and the README describes the engine as memory-bound beyond roughly 100,000 rows.
API security: The README says the backend API has no authentication and assumes it is bound to localhost.
Intended users: The project describes itself as intended to make record linkage usable by data stewards and teams without specialist record-linkage expertise.
License: The repository lists an MIT license.

Claim it for free: prove the domain, then correct facts, plans and screenshots. An editor reviews every change.