+ About +
++ 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. +
+ ++ 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. +
+ ++ 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. +
+ ++ 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 + + . +
+ ++ If you've got a repetitive desktop workflow, bring + it to a 15-minute call and we'll tell you whether + compiling it makes sense. +
+ + Book a demo + ++ Compare +
++ There are three common ways to automate desktop work today: + traditional RPA platforms, AI agents that operate a + computer with a large model, and browser recording tools. + OpenAdapt takes a fourth approach. It compiles a recorded + demonstration into a deterministic script that replays for + free and heals itself when the UI drifts. Each approach + wins somewhere, so here's the honest version. +
+ ++ Platforms like UiPath, Automation Anywhere, and Blue Prism + ask you to build the automation by hand. You author + selectors, arrange flowcharts in a studio, and maintain + both. Large enterprises run a lot of automation this way + and it works, until the UI changes. A vendor ships an + update, the selectors stop matching, and someone has to + open the studio and repair the flow. Licensing is + typically per robot or per seat, and the platforms are + proprietary. +
++ OpenAdapt skips the authoring step entirely. You record + yourself doing the task once, and the compiler turns that + demonstration into a script. When the UI drifts, OpenAdapt + heals the script and proposes the fix as a reviewable + diff, not a broken bot and a support ticket. It runs on + your own machines and it's MIT-licensed open source. +
+ ++ Cloud agents in the OpenAI Operator and Claude + computer-use family re-reason through your task with a + large model on every single run. On tasks nobody has seen + before, they're genuinely impressive. For repetitive + work, though, re-reasoning is the wrong shape. Every run + is slow. Every run can take a different path than the + last. Every run is billed. And most of these services work + by sending screenshots of your screen to the cloud. +
++ OpenAdapt uses a model at compile time and at heal time, + never on a healthy run. A healthy run is a deterministic + local replay: same steps, same order, no model calls, no + per-run bill. Your screen stays on your machines. +
+ ++ Tools like Skyvern and browser-use record or drive + workflows inside the browser, using DOM selectors or model + inference. If your whole workflow lives in a browser tab, + they're worth a look. The limit is structural: + browser-only tools can't reach the desktop EMR, the + Windows loan origination system, or anything delivered + over Citrix. +
++ OpenAdapt works from pixels and inputs rather than the + DOM, so the same approach extends past the browser to + desktop applications and VDI/RDP sessions (adapters for + these are in progress). Recording, compiling, and + replaying all happen on your infrastructure. +
+ +| + | + OpenAdapt + | ++ Traditional RPA + | ++ Computer-use agents + | ++ Browser recorders + | +
|---|---|---|---|---|
| + {row.dimension} + | ++ {row.openadapt} + | ++ {row.rpa} + | ++ {row.agents} + | ++ {row.browser} + | +
+ We'd rather tell you this than have you find out + mid-pilot. Computer-use agents are the better tool for + novel one-off tasks, since compiling a demonstration + is overhead when there's no second run. They win + on tasks you can't demonstrate yourself, and on + exploratory work like researching something across a + dozen unfamiliar sites. OpenAdapt is built for the + opposite case: work your team does the same way, over + and over, where determinism and cost matter more than + improvisation. +
++ The fastest way to compare is to bring a real task. + Book 15 minutes, or read the code first. +
+