Developer Guide
Working with OpenAdapt
Last updated
Working with OpenAdapt
Last updated
OpenAdapt requires Python3.10, you can download it or try our installer, which will download Python for you.
First, clone & navigate to the repository:
If is not installed, you can use pip to install it:
Lastly, run these lines to setup the environment:
See how to set up system permissions on macOS .
Run this in every new terminal window once (while inside the OpenAdapt root directory) before running any openadapt commands below. This is required to activate the pythom environment:
poetry shell
You should see the something like this:
Notice the environment prefix (openadapt-py3.10).
python -m openadapt.entrypoint
CLI would look something like this after the command
After it runs successfully, you will see an app tray at top right of screen
Create a new recording by running the following command:
To make your first recording, try the following command:
Wait until all three event writers have started:
To stop recording, focus the terminal and send CTRL+C (SIGINT). The recording is finished saving when you see something like this:
Current limitations:
Quickly visualize the latest recording you created by running the following command:
python -m openadapt.visualize
This will generate an HTML file and open a tab in your browser that looks something like this:
For a more powerful dashboard, run:
python -m openadapt.app.dashboard.run
For a desktop app-based visualization, run:
python -m openadapt.app.visualize
This will open a scrollable window that looks something like this:
You can play back the recording using the following command:
python -m openadapt.replay NaiveReplayStrategy
Other replay strategies include:
python3 -m openadapt.start
Recording should be short (i.e. under a minute), as they are somewhat memory intensive, and there is currently an describing a possible memory leak.
The only touchpad and trackpad gestures currently supported are pointing the cursor and left or right clicking, as described in this
Read more on .
: Early proof-of-concept which uses the OpenAI GPT-4 API with prompts constructed via OS-level window data.
: Uses to segment active window.
: Assumes the model is capable of directly reasoning on states and actions accurately. With future frontier models, we hope that this script will suddenly work a lot better.
See for a complete list. More ReplayStrategies coming soon!
