Skip to content
Trending storyDeveloping

Alibaba Tongyi MAI-UI team open-sources OpenGCUA computer-use agent stack

1 article1 sourcesince Oct 18Last article 1h ago ·

Overview

AISummary of 1 article

Alibaba's Tongyi MAI-UI team has open-sourced OpenGCUA, a full stack for a generalist computer-use agent, according to a post by X user meng shao.

The release includes a harness, a cross-device SDK, a native macOS app, evaluation trajectories, and a reference agent implementation. The source is at github.com/Tongyi-MAI/OpenGCUA.

The post says the agent decides when to take screenshots, writes Python programs that combine GUI operations, API calls, and shell commands, and maintains its own todo list.

Written by AI from the articles below · updated Oct 18, 9:58 PM ET

Check the sources:

Latest developmentOct 18, 9:54 PM ET
Alibaba's Tongyi MAI team open-sources OpenGCUA, a generalist computer-use agent stack

Article timeline

The articles in this story. Times are ET.

Oct 18
  1. meng shaoXPick
    Alibaba's Tongyi MAI team open-sources OpenGCUA, a generalist computer-use agent stack

    AIAlibaba's Tongyi MAI team has open-sourced OpenGCUA, a full stack for a generalist computer-use agent, including a harness, cross-device SDK, native macOS app, evaluation trajectories, and a reference agent. The post says the model decides when to take screenshots, writes Python programs that combine GUI operations, API calls, and shell commands, and maintains its own todo list.

    Image from @shao__meng's post

Heat Trend

Not enough continuous observations to show a trend yet.