Tongyi-MAI/OpenGCUA
Can I trust it?
Worth a closer look before you use it.
Warnings Check
Very new: it was created 5 days ago. Wait a little before installing it.
Stars from real accounts No data
We haven't checked its stars for fakes yet.
Active OK
Last change today.
Licence OK
Apache-2.0: you can use it for free, also in a commercial product. Keep the licence notice.
Quick checks from public data. They help, but they are no guarantee.
What it is
A research preview of an open-source stack for generalist computer-use agents that combine code execution, GUI interaction, shell access and app APIs to complete tasks on a computer. It includes an OSWorld integration example, a preliminary macOS harness that runs an agent on a…
Who it's for
Researchers and developers building or evaluating computer-use agents on macOS and OSWorld-style benchmarks
How to use it
Ask your AI to set it up
Paste this into Claude, ChatGPT or your coding assistant.
Help me install and set up Tongyi-MAI/OpenGCUA in my project. Follow its README: https://github.com/Tongyi-MAI/OpenGCUA. Explain each step and check it is safe before running anything.
Star curve
Get alerts for repos like this
We'll email you when something in AI agents starts rising. Free, once a week, only what matches.
18,266 GitHub repos watched and ranked every hour. Figures as of 20 October 2026.
What arrives: one email on Mondays with the repos that match, never more. See last week's. Privacy
For maintainers
Add this badge to your README. It shows the repo's place on the radar, updates every hour and links back to this page.
[](https://repoalerts.com/repo/Tongyi-MAI/OpenGCUA?ref=badge)Similar repos
- openJiuwen-ai/jiuwenswarm
A multi-agent system built on openJiuwen that decomposes complex tasks through a Leader agent and specialized teammates, runs on one machine or a cluster, and accepts requests via browser, terminal, o
- ling-stack-org/ling-stack
Local-first workspace where users bring their own AI models and run teammates in a shared project channel. Keeps conversations, tool approvals, artifacts, and final reports together. Source-first alph
- mw00/project-maya
A C++ engine, server and dashboard for running the GLM-5.3-Flash and DeepSeek-V4.1-Flash models locally on one to sixteen NVIDIA or AMD GPUs, on Linux or Windows. It offers OpenAI- and Anthropic-compa
- Aoisop/mawoagent
A local Python agent runtime with a web workbench and CLI that connects model inference, tool execution, permission checks, session resume, long-term memory and Skills. It can turn explicit user feedb
- OpenSparX/MasterAgent
A C++17 agent runtime that matches exact-phrase skills before any model call and validates tool names and arguments before executing them. It can use an explicitly configured local model server, and o
- fy-agent/fyagent
A local desktop app that centralizes configuration for AI coding tools such as Codex, Claude Code and OpenCode. It manages models and providers, accounts, Skills, MCP services, prompts and memory file