Developing Open Source Tools for

Differential Privacy

OpenDP is a community effort to build trustworthy, open-source software tools for statistical analysis of sensitive private data. These tools, which we call OpenDP, offer the rigorous protections of differential privacy for the individuals who may be represented in confidential data and statistically valid methods of analysis for researchers who study the data. 

The 2025 OpenDP Community Meeting is on Friday, September 19th 2025!

REGISTER NOW

Join us in Dublin, Ireland for the 2025 OpenDP Community Meeting where the event will be held at the Dublin Royal Convention Center followed by a cocktail reception!

Explore the Community Meeting agenda and resources!
Read a recap of the 2024 event!

Featured Resources

Use Our Tools

Do you have data to share or an application that can benefit from differential privacy? We can help. 

Summer Interns Program

Are you an undergraduate or grad student interested in advancing differential privacy? Apply to join us this summer!

Visiting Fellows Program

Are you an established engineer or scholar looking for a part-time opportunity to engage with differential privacy? Apply to work with us!

Working Groups

Want to be part of a group of community members focused on technical discussions, sharing ideas, or collaboratively working on a project? Click here to learn more and join!

Join us on ourSlackGithub,andMailing List

Upcoming Events

Latest News

  • 2025 OpenDP Community Meeting Recap
    Read on to catch up with the highlights of the 2025 OpenDP Community Meeting and find out how you can get involved with our community!…
  • Announcing DP Wizard v0.5
    Complementing the v0.14 release of the OpenDP Library, we’d also like to announce v0.5 of DP Wizard, a user interface that makes it easier to get started with differential privacy….
  • Announcing OpenDP Library 0.14
    We’re happy to announce v0.14 of the OpenDP Library!  This release has a number of features that make common analyses easier and more idiomatic, including identifier truncation, synthetic data generation, and linear regression, as well as enhancements to the framework like odometers and additions to the suite of core differentially private mechanisms….

The work of OpenDP would not be possible without the generous support of many organizations.

See a list of recent OpenDP financial supporters.