FIDENIT
OPEN SOURCE · Planned

Data Core

Turning mixed files into structured data

PROBLEM

Could any kind of data be used right away, just by connecting it?

Data in every format, such as spreadsheets, PDFs and logs, usually has to be cleaned up before AI can use it. We want to build that cleanup step as open source and share it with others who do the same work by hand. As with KITE, we would like to keep it open and refine it together.

HOW IT WORKS
01 · INPUT

Connect

Spreadsheets · PDFs · databases · logs

02 · ENGINE

Refine · Calculate

We aim to recognize formats and clean duplicates and errors, then have agents infer the structure and check each other's work.

03 · OUTPUT

Result

Cleaned, structured data

GOALS
01

Recognizing formats

02

Inferring structure

03

Cleaning duplicates and errors

04

Serving data by API

SPEC
FieldOpen source
StatusPlanned
InputSpreadsheets · PDFs · databases · logs
OutputCleaned, structured data
DeliveryGitHub open source (goal)
MORE IN OPEN SOURCE

Let's talk about
Data Core

business@fidenit.com