Welcome to OpenAdapt! This Python library implements AI-First Process Automation with the power of Transformers by:
- Recording screenshots and associated user input
- Aggregating and visualizing user input and recordings for development
- Converting screenshots and user input into tokenized format
- Generating synthetic input via transformer model completions
- Replaying synthetic input to complete tasks
The goal is similar to that of Robotic Process Automation, except that we use transformers instead of conventional RPA tools.
The approach is similar to adept.ai, except that instead of requiring the user to prompt the model directly, we prompt it behind the scenes by observing the user's activities.
git clone https://github.com/MLDSAI/OpenAdapt.git
cd OpenAdapt
python3.10 -m venv .venv
source .venv/bin/activate
pip install wheel
pip install -r requirements.txt
pip install -e .
alembic upgrade head
pytest
Create a new recording by running the following command:
python -m puterbot.record "testing out puterbot"
Wait until all three event writers have started:
| INFO | __mp_main__:write_events:230 - event_type='screen' starting
| INFO | __mp_main__:write_events:230 - event_type='input' starting
| INFO | __mp_main__:write_events:230 - event_type='window' starting
Type a few words into the terminal and move your mouse around the screen to generate some events, then stop the recording by pressing CTRL+C.
Note: keep your recording short (i.e. under a minute), as they are somewhat memory intensive, and there is currently an open issue describing a possible memory leak.
Visualize the latest recording you created by running the following command:
python -m puterbot.visualize
This will open your browser. It will look something like this:
You can play back the recording using the following command:
python -m puterbot.replay NaiveReplayStrategy
More ReplayStrategies coming soon! (see Contributing).
Our goal is to automate the task described and demonstrated in a Recording
.
That is, given a new Screenshot
, we want to generate the appropriate
InputEvent
(s) based on the previously recorded InputEvent
s in order to
accomplish the task specified in the Recording.task_description
, while
accounting for differences in screen resolution, window size, application
behavior, etc.
If it's not clear what InputEvent
is appropriate for the given Screenshot
,
(e.g. if the GUI application is behaving in a way we haven't seen before),
we can ask the user to take over temporarily to demonstrate the appropriate
course of action.
The dataset consists of the following entities:
Recording
: Contains information about the screen dimensions, platform, and other metadata.InputEvent
: Represents a user input event such as a mouse click or key press. EachInputEvent
has an associatedScreenshot
taken immediately before the event occurred.InputEvent
s are aggregated to remove unnecessary events (see visualize.)Screenshot
: Contains the PNG data of a screenshot taken during the recording.WindowEvent
: Represents a window event such as a change in window title, position, or size.
You can assume that you have access to the following functions:
create_recording("doing taxes")
: Creates a recording.get_latest_recording()
: Gets the latest recording.get_events(recording)
: Returns a list ofInputEvent
objects for the given recording.
Join us on Slack. Then:
- Fork this repository and clone it to your local machine.
- Get OpenAdapt up and running by following the instructions under Setup.
- Look through the list of open issues at https://github.com/MLDSAI/OpenAdapt/issues and once you find one you would like to address, indicate your interest with a comment.
- Implement a solution to the issue you selected. Write unit tests for your implementation.
- Submit a Pull Request (PR) to this repository. Note: submitting a PR before your implementation is complete (e.g. with high level documentation and/or implementation stubs) is encouraged, as it provides us with the opportunity to provide early feedback and iterate on the approach.
Your submission will be evaluated based on the following criteria:
-
Functionality : Your implementation should correctly generate the new
InputEvent
objects that can be replayed in order to accomplish the task in the original recording. -
Code Quality : Your code should be well-structured, clean, and easy to understand.
-
Scalability : Your solution should be efficient and scale well with large datasets.
-
Testing : Your tests should cover various edge cases and scenarios to ensure the correctness of your implementation.
-
Commit your changes to your forked repository.
-
Create a pull request to the original repository with your changes.
-
In your pull request, include a brief summary of your approach, any assumptions you made, and how you integrated external libraries.
-
Bonus: interacting with ChatGPT and/or other language transformer models in order to generate code and/or evaluate design decisions is encouraged. If you choose to do so, please include the full transcript.
If you're interested in getting paid for your work, please mention it in your Pull Request.
Apple Silicon:
$ python puterbot/record.py
...
This process is not trusted! Input event monitoring will not be possible until it is added to accessibility clients.
Solution: https://stackoverflow.com/a/69673312
Settings -> Security & Privacy
Click on the Privacy tab
Scroll and click on the Accessibility Row
Click the +
Navigate to /System/Applications/Utilities/ or wherever the Terminal.app is installed
Click okay.
alembic revision --autogenerate -m "<msg>"
Please submit any issues to https://github.com/MLDSAI/puterbot/issues with the following information:
- Problem description (please include any relevant console output and/or screenshots)
- Steps to reproduce (please help others to help you!)