OpenAdapt.AI
Show it once. It runs forever. On your premises.
OpenAdapt compiles a recorded demonstration into a deterministic, self-healing automation — open source, auditable, and running entirely on your own machines.
Register for updates (we promise not to spam)
How it works
A demonstration compiler: one recording in, a deterministic automation out.
- 1.0
Record
Do the task once while OpenAdapt captures screens and inputs.
- 2.0
Compile
The demonstration becomes an editable script: visual anchors, per-step assertions, parameters.
- 3.0
Run
Deterministic replay in milliseconds, locally, no per-run model calls.
- 4.0
Self-heal
When the UI drifts, a fallback ladder finds the target and proposes the fix as a diff.
- 5.0
Audit
Every run produces an illustrated report: what ran, what it saw, what changed.
OpenAdapt v1 is open source and under active development. Commercial pilots for healthcare and lending are open.
Getting Started
OpenAdapt is an open-source demonstration compiler for desktop automation. Record a workflow once and it compiles into a deterministic, self-healing automation that runs on your own machines.
Install in 30 Seconds
One command installs everything you need. No Python setup required.
$curl -LsSf https://astral.sh/uv/install.sh | sh$uv tool install openadapt$openadapt --help
What is uv? - uv is a fast Python package manager that automatically installs Python and manages dependencies.
Quick Start Commands
openadapt doctorVerify your setupopenadapt capture start --name my-taskRecord a demonstrationopenadapt capture stopStop recordingopenadapt capture view my-taskReview what was capturedRecording and review ship in the open-source package today. The compiler stage — turning a recording into a deterministic, self-healing automation — is in private preview: book a demo for early access.
PyPI Download Trends
Historical download statistics for OpenAdapt packages
Register for updates (we promise not to spam)
What's Next?
Troubleshooting
The OpenAdapt Ecosystem
Open-source repositories
Loading packages...
Evaluation & Benchmarks
We wrap official benchmarks like Windows Agent Arena in a CLI that handles VM lifecycle, agent execution, and step-by-step inspection — so you can iterate on your agent fast without modifying the original benchmarks.
The benchmark viewer lets you replay every step of an evaluation — screenshots, actions, and execution logs. View on GitHub
Built for regulated back-offices
Record the workflow once and OpenAdapt compiles it into an automation your team can review, run, and audit — entirely on your own machines. No brittle selectors to hand-author. No per-run model costs.
Built-in PII/PHI scrubbing keeps your sensitive data safe.
Healthcare clinics
- Referral and fax intake, EMR data entry and extraction — desktop and VDI EMRs included. PHI handling stays fully local.
Mortgage & lending ops
- Loan-file data extraction and entry in desktop LOS software like Encompass. Borrower data stays in your environment.
Let us build for you
If OpenAdapt doesn't fully automate your workflow out of the box, we'll work with you to fix that.
Start IntakeFrequently asked questions
- What is OpenAdapt?
- OpenAdapt is an open-source demonstration compiler for desktop automation. You record yourself doing a task once, and OpenAdapt compiles that recording into a deterministic, self-healing script that runs on your own machines. Healthy runs make no cloud model calls, so each run costs nothing.
- How is OpenAdapt different from RPA tools like UiPath?
- Traditional RPA makes you hand-author brittle selectors and flowcharts, and the bot breaks when the UI changes. OpenAdapt compiles the automation from a demonstration instead — no selector authoring — and when the UI drifts it heals itself, proposing the fix as a reviewable diff. It also runs entirely on your machines.
- How is OpenAdapt different from AI computer-use agents?
- Computer-use agents re-reason through your task with a large model on every run, so they are slow, non-deterministic, and bill you per run. OpenAdapt compiles the task once and replays it deterministically for free. A model is only invoked to heal the script when the UI drifts.
- Does my data leave my machines?
- No. OpenAdapt is local-first by architecture: recordings, compiled scripts, and replays all stay on your own infrastructure. Nothing is uploaded to run an automation. PII/PHI scrubbing tooling is included for teams that need to sanitize captured data before anyone — human or model — sees it.
- Is OpenAdapt free?
- Yes — OpenAdapt is MIT-licensed open source, free to use and modify. For regulated deployments in healthcare and lending we run commercial pilots with hands-on support: we help compile your first workflows, set up review, and keep the automations healthy. Book a demo to talk about a pilot.
- What software does OpenAdapt work with?
- Anything with a screen. Because OpenAdapt watches pixels and inputs rather than APIs or browser internals, it works with desktop applications, web apps, and software delivered over VDI or RDP — including EMRs and loan origination systems that cloud automation tools can't reach.
Book a 15-minute automation fit call
Tell us your highest-friction workflow and we will map what can be automated first.