Add Yappy (macOS computer-use agent, accessibility-tree based) - #37
Open
Prakshal-Jain wants to merge 1 commit into
Open
Prakshal-Jain wants to merge 1 commit into
Prakshal-Jain wants to merge 1 commit into
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Adds Yappy under Commercial → Frameworks & Models, in the same shape as the neighbouring entries.
Yappy is a computer-use agent for macOS, triggered by voice or typing. What makes it worth listing next to the screenshot-driven agents already here is the observation route: it reads the front window through the macOS accessibility tree, and pages through Chrome and Safari, rather than sending screenshots to a vision model. That is why it can drive a window that is minimised or on another Space without stealing focus.
It can also put TypeSafe's Jev (a System One decision model) in front of the agent, so the per-step choice of operation and target is one typed decision instead of a narrated one.
Measured run, method and caveats published rather than asserted (n=1, disclosed): https://yappy.biz/research/yappy-vs-heyclicky/
Happy to shorten the entry or move it if Commercial is not the right bucket.