OpenAdapt
Compiles a demonstrated GUI task into a program that reports VERIFIED only if an independent check agrees. pip install openadapt; openadapt flow tutorial. Compiler lives in openadapt-flow.
Runssource: GitHubhomepagePythonMITcommit 7ae7ebc02048
Python, MIT licensed. The project labels itself: automation from demonstration, browser automation, citrix, demonstration compiler, desktop automation, deterministic replay, effect verification and gui automation.
OpenAdapt runs. An Argusic agent installed it in 0.3 minutes and hit 2 errors on a clean machine with no GPU, and the whole session was recorded.
Package installs and all 288 tests pass; CLI, doctor, version commands work; recording generates valid artifacts; compile is CPU-bound by onnxruntime in this container but eventually produces bundles.
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 80 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.
What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- onnxruntime pthread_setaffinity_np spams stderr and causes compile/replay to hang in constrained containers
- openadapt flow tutorial hangs during replay phase (onnxruntime OCR thread-spawn issue in this container)
- Install time
- under a minute
- Cold machine to finish
- 20 minutes
- Errors hit and fixed
- 2 hit, 0 fixed with no human help
- How the result was proved
- pytest tests/ --tb=short returned 288 passed, 6 skipped in ~2s
- Model tokens used
- 108,268
- Exact commit tested
- 7ae7ebc02048
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
/bin/sh -lc "cd /work/repo && .venv/bin/openadapt doctor 2>&1 | grep -c \"READY\\|OK\" ; echo \"---… succeeded in 11260ms: 4 openadapt, version 1.16.0 exited 143 in 159811ms: exec /bin/sh -lc 'pkill -f "openadapt" 2>/dev/null; sleep 1; echo done' in /work/repo exited 143 in 0ms: Now I have a thorough understanding of everything. Here's the final report. tokens used 108,268 Now I have a thorough understanding of everything. Here's the final report.
Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Reached a running state on a clean machine, with the session recorded.
- Installed in 0.3 minutes.
- Ran without a GPU, so it does not need one to start.
- Licensed MIT, as reported by its host.
What did not, or is not known
- Hit 2 errors during setup, 2 of which were not solved.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
- A quick evaluation: it was running 0.3 minutes after the clone.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
Topics (from GitHub)
automation-from-demonstrationbrowser-automationcitrixdemonstration-compilerdesktop-automationdeterministic-replayeffect-verificationgui-automationhealthcare-automationlocal-firstprocess-automationpythonrdprpaui-automationworkflow-automationworkflow-compiler
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/openadapt)Questions
- Does OpenAdapt run?
- Yes. OpenAdapt runs. Argusic installed and launched it on a clean machine in 0 minutes, hitting 2 errors on the way, and recorded the session.
- How did Argusic test OpenAdapt?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 7ae7ebc02048. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test OpenAdapt?
- The run that produced this verdict cost $0.22: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does OpenAdapt take to install?
- 0.3 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does OpenAdapt need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing OpenAdapt?
- 2 things broke in the recorded run. Each one, and the time it cost, is listed on this page.
- Where is the evidence for OpenAdapt?
- The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.