What if your computer didnโt just respond to commands, but actually understood how to get work done?
Thatโs the idea behind OpenYabby.
Most AI products still feel like smarter chatbots.
You ask.
They answer.
Then you copy, paste, switch tabs, open files, run commands and finish the workflow yourself.
But real work doesnโt live in one chat window.
It moves across your terminal, browser, filesystem, APIs, local apps and all the small decisions in between.
So with OpenYabby, weโre building something different:
A voice-first operating layer for Mac.
You say:
โYabby, create and ship this landing page.โ
And OpenYabby starts coordinating the work.
It creates a lead agent.
Breaks the request into phases.
Launches specialized sub-agents.
Runs CLI tools.
Reads and edits files.
Uses the browser.
Performs QA.
And manages the execution loop from start to finish.
What excites me most is not just the automation.
Itโs the orchestration.
Agents working in parallel within each phase.
Tasks moving sequentially across phases.
Memory carrying context across sessions.
Real system access through terminal, AppleScript, Playwright and the browser DOM.
Not a staged AI demo.
Actual work happening on your machine.
Weโre also designing OpenYabby around the way people naturally communicate:
-Wake word detection
-WebRTC voice sessions
-Bidirectional audio
-Speaker verification
So instead of constantly typing prompts or clicking through tools, you can simply talk to your computer and delegate.
Itโs still early.
Reliability, safety and execution quality are things weโre improving every day.
But I believe this is where personal computing is going:
From using software to managing intelligent collaborators.
Less manual operation.
More delegation.
Explore OpenYabby:
openyabby.com/
GitHub:
github.com/OpenYabby/OpenYabโฆ
If youโre building, researching or thinking seriously about autonomous agents, multi-agent systems or voice-native computing, Iโd love to connect.