OpenAdapt VS datasette

> Rabbit has said the device will be able to learn any app, if you teach it.

We're building this over at https://github.com/OpenAdaptAI/OpenAdapt. OpenAdapt learns to automate tasks in desktop apps by observing human demonstrations.

Early demo: https://twitter.com/abrichr/status/1784307190062342237 (more coming soon!)

The demo is overly simplistic to keep it short -- it also works with arbitrary applications and operations.

Also, we're open source. Contributions and feedback are welcome and encouraged :)

Very interesting, thank you for making this available!

At OpenAdapt (https://github.com/OpenAdaptAI/OpenAdapt) we are looking into using pm4py (https://github.com/pm4py) to extract a process graph from a recording of user actions.

I will look into this more closely. In the meantime, could the authors share their perspective on whether Memary could be useful here?

See https://github.com/OpenAdaptAI/OpenAdapt for an alternative that works with desktop GUIs.

Not mentioned: learning from demonstration. This is the approach we are taking at https://github.com/OpenAdaptAI/OpenAdapt.

Congratulations on shipping!

Check out https://github.com/OpenAdaptAI/OpenAdapt for an open source (MIT license) alternative that also works on desktop (including Citrix!)

https://github.com/mldsai/puterbot is designed for all desktop applications, including browsers. We're also working on a chrome extension to support reading/writing directly to DOM: https://github.com/OpenAdaptAI/OpenAdapt/pull/364

Simon Willison's github would be a great place to get started imo -

https://github.com/simonw/datasette

I'm a fan on simonw's datasette/dogsheep ecosystem https://datasette.io/

I use Anki the exact same way. After a lifetime of learning I have accepted that I will never read over anything I write for myself voluntarily - so my two options are:

1. Write an article so good I can publish it and look it over myself later on. I did this last year with https://andrew-quinn.me/fzf/, for example.

2. Create Anki cards out of the material. Use the builtin Card Browser or even https://datasette.io/ on the underlying SQLite database in a pinch to search for my notes any time I have to.

Were you aware of, or tempted by https://datasette.io/ for creating your solution?

Browsing HN, GitHub and the like we get to see a huge variety of software products and code bases.

I often see products and think - if this product X, got together with Y, it would be pretty cool - kind of like if they had a kid together.

Not too literally, but more on the conceptual level - my level of programming is low.

E.g. Just some....

- pocketable.io & datasette (+with some more charting) [https://pocketbase.io, https://datasette.io]

You might like the Datasette project: https://datasette.io/

I don't think they are desperate for contributions but it's a welcoming environment and a fun project to hack on. You'll learn a lot just from reading the source and the incredibly informative PRs. The creator is a really talented developer with a great blog which shows up on the HN front page often.

Last year I worked through the challenges using VisiData, Datasette, and Pandas. I walked through my thought process and solutions in a series of posts.

> uploads of boring raw excel data and receive a nice UI

https://datasette.io/