About DatumOS

Construction data deserves a fixed point.

Every site has a datum — the mark all measurements refer to. We started DatumOS because the industry’s commercial data has no such mark: the same position is retyped, reformatted, and re-priced at every handover. We’re building the software that ends that.

The story

From a parser to a platform.

DatumOS began with a concrete problem: German construction tenders arrive as GAEB files that most modern software can’t read properly. So we built pyGAEB — an open-source Python engine that turns every GAEB version and exchange phase into one precise, typed model — and published it under MIT for anyone to use and audit.

Working with door and window manufacturers showed us where that foundation matters most: estimators spending days retyping tenders before they can quote. The DatumOS platform grew out of that work — upload a tender in any format, get a priced, reviewable, send-ready quote back in minutes.

The destination is bigger: one record every commercial workflow reads from — and specialized agents on top that prepare each of those workflows, from bid comparison to change orders, for human judgment. Germany first, because GAEB gives structured data a head start. Then everywhere estimates still live in PDFs.

Who’s behind it

A team of four, close to the trade.

We come from building LLM applications in production; DatumOS applies that experience to construction’s commercial data. We build the platform, the open-source engine, and the pilots ourselves — the people you meet in a pilot are the people who write the code.

Kalyanakannan Padivasu

Senior software engineer with over a decade of building Python systems — Django and FastAPI backends, cloud infrastructure, and LLM-powered pipelines. Has led and mentored engineering teams delivering large-scale production platforms.

Dhiyaneshwar Chandrasekaran

Technical lead with eight-plus years across e-commerce and financial services, specialized in Python microservices, Kubernetes, and large-scale data pipelines with Spark and Airflow. Takes complex distributed systems from first design to reliable production.

Swathi Narayanan

Software engineer with eleven years in the industry, spanning product development and senior solution support across Python, Java, C#, and C. Brings the discipline of keeping enterprise software dependable for demanding customers.

Sureshkumar Sreedharan

Senior engineer with eleven years of experience driving product development across the Python, Java, and Angular ecosystems. Dedicated to translating complex business requirements into reliable, production-grade applications.

Talk to us directly.

No sales team, no ticket queue — you talk to the people who build the product. Whether you want a pilot, an integration, or just to sanity-check an idea about GAEB tooling.

Get in touch →