OpenAdapt

Give your agent a program, not a mouse.

The open-source, verified execution layer for computer-use agents.

What it can do · Documentation · Quickstart · Live demo · Website · Get updates · Discord

A computer-use agent looks at the screen and chooses every click again, on every run. OpenAdapt lets your agent, or a person, do a task once in a web, Windows, macOS, Linux or remote-desktop app. It compiles that run into a program, and your agent calls the program as one tool. The program runs with no model calls and sends no screenshots anywhere. It confirms the right record before each save, reads the save back from the system of record after it, and returns a plain outcome. When anything doesn't match, it stops and tells your agent instead of guessing.

Measured on OpenEMR and openIMIS

One new-patient referral in a test copy of OpenEMR, the open-source EHR whose 7.0 release is ONC-certified, timed from a fresh browser through sign-in, the entry and the saved record read back (median):

Who does the entry	Time per referral	Saved correctly	Model cost
Agent alone (Claude Sonnet 5.5 computer use)	██████████████████ 36.5 s	62 of 63	about $0.08
OpenAdapt program, screen steps	███████████ 22.5 s	18 of 18	$0
OpenAdapt program, API step	██ 3.3 s	18 of 18	$0

The API step replaces the program's 41 screen steps with the one form submission the app itself sends, then reads the record back. In both program rows a possible-duplicate referral stopped without saving, as it should. Both program rows ran on 19 Oct on one copy of the app, interleaved, with the approval gate off; the benchmark harness admitted the API step. The agent row is the 14 to 15 Oct timing study, on its own copy of the app. SCOREBOARD.md has every run.

On a test copy of openIMIS, the open-source insurance and claims system that runs Nepal's national health insurance scheme, the compiled program entered 149 synthetic claims with no model calls: 148 read back correct and none were saved wrong (SCOREBOARD.md).

A screen can't show a save that went wrong behind it. On a test copy of OpenEMR, with faults injected in its database (a field blanked, a value changed, a duplicate chart, a chart removed, another chart deleted or edited), the agent claimed success on all 30 bad saves. Reading the record back caught 25 of the 30 and confirmed all 5 clean saves, with no false alarms. On MockMed, a test app that shows a save as done before its server answers, the agent also claimed all 30 bad saves, and the read-back caught all 30 (details below).

One harness, three modes

Mode	What happens	Model calls
Explore	Your agent, or a person, does the task once while OpenAdapt records every action. The save is read back before anything compiles.	Your agent's, on your own key
Run	The compiled program repeats the task with new inputs. It checks the record before each save and reads it back after.	None
Repair	When the app changes, the run stops before saving. An agent shows the fix, the program tries it up to the save without saving, and a person approves it.	Only when something changed, on your own key

Why the read-back matters

A success screen is not proof of a save. We injected 8 kinds of bad save into a test app (a save that never landed, landed partly, landed twice, went to the wrong record, or changed another record), 9 runs each, alongside clean runs. Each check below was asked whether those 72 bad saves had succeeded:

How the save was checked	Bad saves reported as saved
The app's "Saved" message on screen	54 of 72
A read of the record over the app's REST API	9 of 72 (all writes to a table it didn't read)
A read of every table in the database	0 of 72

EFFECT_E2E.md has the fault set, the method and the raw results.

This is the beginning of the README. Read the rest at the original. Read the full README ↗