Your machine
Local
$0
MIT engine on your machine. Record, compile, replay. No account.
- Record, compile, replay
- No account
Start locally
pip install openadapt
Verified last-mile execution for agents.
Automate the GUI work your systems still make people do.
Compile a demonstration into a program an agent can invoke and verify.
Free locally · MIT
A 55-second story
She shows the task once. The program checks the record.
Maria shows the task once. It watches and turns it into a small program that runs with no AI in the loop. Before it says anything worked, it checks the record, even when the screen already says Saved. An expired policy stops the workflow. She decides on her phone.
Reenactment. Product footage uses synthetic patient data. The Maria scenes and music use generative AI.
Read the transcript
- Every shift, Maria retypes the same patient details into the same five screens.
- She'll do it about a hundred times today.
- None of it is hard, but she's tired, and one wrong click files the wrong note in the wrong chart.
- So one afternoon, she shows OpenAdapt the task instead.
- It watches and turns it into a small program.
- Now the program runs on its own, no AI in the loop.
- And before it says anything worked, it checks the patient's record.
- When OpenAdapt sees that the policy has expired, it stops before it sends anything.
- The program asks Maria to decide.
- She checks the chart on her phone and approves.
- The decision is on the record, and Maria gets on with her day.
- OpenAdapt is free to use locally.
- Your first workflow takes about five minutes.
- Get started at openadapt.ai/start.
See it run
The same program, twice.
One time the write lands and you get a Seal. One time openadapt quickstart --break-it stops the run.
In a fault-injection study, screen-only checking accepted 54 of 90 wrong results. A complete system-of-record read accepted 0 of 90. Read the study
OpenAdaptObservingStep 1 of 6Observing the application
0:00 / 0:00Evidence
Guided view synchronized to the exact retained runtime timeline; raw footage remains unchanged.
- 1DemonstrateCapture the task and its evidence.
- 2ExecuteReplay the compiled workflow locally.
- 3Verify or haltProve the effect, or stop for review.
Same halt on your machine: openadapt quickstart --break-it
How it works
Demonstrate, compile, check the effect, then VERIFIED or halt
You or the AI you already talk to can demonstrate. A person still has to admit the program. After that, the agent calls it and healthy runs make no model calls.
- 1
Demonstrate
Record one bounded workflow in its real application. You can show it, or the AI you already talk to can. A person still has to admit the program.
- 2
Compile
The recording becomes a program the agent can invoke. Review the steps, identities, expected results, and environment before you reuse a version.
- 3
Check the record
Before it says it worked, a separate read proves whether the change landed. That check may use an API, a database, a file, or a second session.
- 4
VERIFIED or halt
The run reports VERIFIED only when that check passes. If it can't prove the effect, it stops.
Inside the program
See the program compare recorded evidence with the live application.
OpenAdapt ties each compiled action to the evidence that created it. Play the exact trace below, or switch to the safety halt. It won’t act when the current evidence can’t prove one safe target.
Inspect the full methodProgram State ConsoleRepresentative synthetic program
v3
8d9c…42afpublic syntheticProgram artifact
- Recorded evidence
- Compiled program v3
- Repair candidate v4
- Review and trials
- Active v4
One live run
- 1Current observation
- 2Resolve target
- 3Identity gate
- 4Act once
- 5Screen check
- 6Effect check
- RUNNING
ObserveInput contract accepted
event 01OpenAdapt Cloud
Approved workflows, runs, and evidence summaries
When a run needs a person, it asks, on your phone. The answer and the evidence summary stay attached to the run.
Human decision
Ask a person when the workflow reaches a real judgment call.
OpenAdapt pauses at an approved policy choice and asks one authorized person one clear question. Before it continues, the runner checks the live application again.
See the full human judgment demoA strong first workflow
Start with a job you already run, whose last write is on the screen
- No practical write API for the last mile. If a supported API exposes the operation, use it.
- A wrong action has operational, financial, or compliance cost. Where a wrong write costs nothing, a cheaper tool wins.
- You already know the transaction. Same job, new values each run.
Browser, desktop, and remote
The same loop on browser, desktop, and remote
Each workflow bundle binds one target and one execution backend. You can record, compile, and prove a result on these surfaces today. A task that crosses a boundary uses separate bundles, external orchestration, and an end-to-end result check.
Browser
Any web application.
Native desktop
Windows, macOS, and Linux applications.
Remote applications
RDP, Citrix, and VDI sessions.
Run it on our managed runners, or entirely inside your own boundary. Need a hosted runner? Talk to us.
Production is a signed admission you earn. The public lifecycle record currently lists all seven product targets with no admission. Start locallyStart a sprintSee the ledgerproduction-lifecycle.json
What each surface uses, and what it supports todayReview the security boundary
Customer result
Recovering missed billables with automated RVU audits
OpenAdapt now handles the repetitive EMR evidence collection and spreadsheet reconciliation behind Dr. Victor Abrich’s monthly RVU audits. The workflow helps recover about $75,000 a year in missed billables and saves several hours of physician time each month.
Dr. Victor Abrich, MD
Board-certified cardiac electrophysiologist
A US cardiology electrophysiology practice
Disclosure: Dr. Abrich is the founder’s brother. This is OpenAdapt’s founding deployment, not independent validation.
Read the case study≈$75,000
in missed billables recovered per year
Several hours
of physician audit work saved each month
More complete
audits than manual review alone
Pricing
Local is free. Hosted is $29 / month.
Where it runs. Local stays $0. Hosted is $29 / month if you want us to leave a machine on.
Our machine
Hosted
$29/ month
OpenAdapt Cloud: we run the machine.
- Managed runner
- Dashboard and run history
- API key and verify URL
- Your agent can call it
The runner is ours. The Seal still comes from the verified run.
Your runtime
Enterprise
Talk to us
Send one workflow, one app, and one environment. We review it and reply go or no-go.
- One app, one environment, qualified
- Identity and effect checks
- Customer-controlled or dedicated runner
- BAA and a private verify URL
- Citrix, VDI, volume, SLA
A Seal is the signed receipt that the write landed. Local is $0. Hosted is $29 / month. See one.
FAQ
- Can I run locally without paying?
- Yes. pip install openadapt, then openadapt quickstart. Record, compile, and replay on your machine. No account.
- Do I have to use your hosting?
- No. Run it on your machine. Hosted is optional if you want us to run the machine.
- What do I pay for on Hosted?
- The machine. Hosted is $29 / month. The runner is ours. The Seal still comes from the verified run.
- What is Qualification?
- A review that gets a workflow into Enterprise. You send one workflow, one app, and one environment. We reply go or no-go. Start on /qualify.
Data and control
Keep sensitive work in the boundary you approve
- Customer-controlled execution for sensitive and remote work
- Local processing for live screenshots, OCR, identities, and secrets
- Explicit network and model policy for Standard and Regulated profiles
- Signed, sealed, versioned, and independently verifiable artifacts
- Evidence-backed VERIFIED or HALTED outcomes
- MIT-licensed local runtime, plus a hosted Cloud control plane
Workflow fit review
See if one workflow fits
Tell us the task and how you check the result today. You get an honest answer on fit, the risks, and how it would run.
Start the fit review