DMP Chef

A Python pipeline for crafting Data Management Plans (DMPs)

Overview

DMP Chef is an open-source (MIT License), Python-based pipeline that leverages AI to draft funder-compliant Data Management Plans (DMPs). Researchers often struggle to write DMPs because they require advance knowledge of data types, metadata standards, repositories, and funder-specific sharing requirements. DMP Chef addresses this challenge by translating high-level project descriptions into funder-compliant DMP, using a tailored prompt, funder templates, funder guidelines, and a large language model (LLM). This project is part of a broader extension of the DMP Tool platform.

This website is meant to provide information about the DMP Chef pipeline and also provide a testing interface. The ultimate goal is to integrate the DMP Chef pipeline into the DMP Tool platform, providing researchers with a familiar and convenient user interface that does not require any coding knowledge.

Team

DMP Chef is developed by the FAIR Data Innovations Hub in collaboration with the California Digital Library (CDL) who are developing and maintaining DMP Tool platform.

FAIR Data Innovations Hub

California Digital Library

DMP Tool

Project Roadmap

Oct 2025 – Mar 2026

Phase 1

Define the user workflow, test improvement strategies, and build the Alpha prototype to draft NIH-compliant DMPs. This phase ends with internal testing and refinement.

Apr 2026 – Sep 2026

Phase 2

Add general-purpose and multi-funder DMP drafting capabilities (e.g., NSF) and deliver the Beta prototype. This phase ends with external user testing and refinement.

TBD

Phase N: Integration with DMP Tools

Integrate the DMP Chef back-end with DMPTool.org

Funding

This project is a National Science Foundation (NSF) and Chan Zuckerberg Initiative (CZI)-funded collaboration between the FAIR Data Innovations Hub and California Digital Library (University of California Office of the President) as part of a broader extension of the DMP Tool platform.