About

About OpenAdapt

OpenAdapt is an open-source demonstration compiler for desktop automation. You record yourself doing a task once, and it compiles that recording into a deterministic script that replays on your own machines. Healthy runs make no cloud model calls; a model is only invoked to heal the script when the UI drifts, and the fix is proposed as a reviewable diff. That's the whole idea, and everything we build serves it.

Who's behind it

OpenAdapt is built by MLDSAI Inc., founded in Toronto in 2023. The founder is Richard Abrich, a machine learning engineer who has been building OpenAdapt in the open since the first commit. There's no stealth roadmap. The issues, the pull requests, and the mistakes are all public on GitHub.

Open source, actually

The code lives in the OpenAdaptAI organization on GitHub, split into focused packages: openadapt-capture for cross-platform recording, openadapt-privacy for PII/PHI scrubbing, openadapt-ml for models, and the openadapt meta-package on PyPI that ties them together. Everything is MIT-licensed. Use it, fork it, ship it, no permission needed.

How to reach us

Email hello@openadapt.ai and a person will reply. For bugs and feature requests, open an issue on GitHub. For everything else, there's Discord.