Tongyi-MAI/OpenGCUA
An open-source stack for generalist computer-use agents, combining code execution, GUI interaction, and cross-device control.
Older snapshot: check the original source for current information.
From the publisher
README & documentation
Source previewRead the project’s overview, installation instructions and usage examples. The original README is the source of truth.
[](https://tongyi-mai.github.io/OpenGCUA/) [](https://arxiv.org/abs/2610.22200) [](https://tongyi-mai.github.io/OpenGCUA/trajectories.html) [](#quick-start) [](LICENSE) [](#community) [](#community) News · Results · Demos · Quick start · SDK · Open stack · How it works · Contributing · Contact Computer use has reached a turning point. GPT-6 Astra's demos offered an exciting vision of what computer-use agents could make possible, and the focus is expanding from GUI-only interaction to both visual and programmatic interfaces. The question has changed, from how well a model operates a GUI to how well a system completes work on a real computer by whatever means works. We call such a system a generalist computer-use agent (GCUA). It uses a computer in more ways than you do. It reads the accessibility tree and calls app APIs, runs shell commands, and operates the GUI when it needs to. With code execution, it writes GUI operations as code and combines them with all of these in one program, with…
Read the full README ↗ · Preview checked 2026-10-31T02:58:07.849Z
Inside the original README — Document outline
- GPT-6 made computer use the frontier. We make it open.
- 🔥 News
- 📊 Results
- 🎬 Demos
- 🚀 Quick Start (macOS source harness)
- Agent Skills
- Native macOS app
- 🔌 Cross-Device SDK
- 🗺️ The open stack and what comes next
- 🧩 How it works
- 🤝 Contributing
- 👥 Community
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the README
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
- ![Paper
- ![License
- Quick start
- OSWorld integration example
- paper
- ![Side-by-side video of four workflows filling in the same visa form.
- ![OpenGCUA researching hotel room options in a desktop browser.
- ![OpenGCUA performing GUI actions on a visa form in macOS Preview.
- uv
- Setup, configuration, and troubleshooting
- error-indexed troubleshooting guide
- SDK guide
Documentation belongs to its respective authors. Reported project/model license: Apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
What this repository does
An open-source stack for generalist computer-use agents, combining code execution, GUI interaction, and cross-device control.
Repository facts
- Owner
- Tongyi-MAI
- Primary language
- HTML
- Stars
- 418
- Forks
- 33
- Open issues + pull requests
- 0
- License
- Apache-2.0
- Archived
- No
- Default branch
- main
- Created
- 2026-10-15T09:03:56.000Z
- Last push
- 2026-10-21T01:31:11.000Z
Topics and intended use
No topics were included in the latest source metadata.
Review the README for scope, installation, examples and limitations. We do not run repository code or certify it.
Evaluate before installing
Review licensing and dependencies, inspect recent commits and unresolved issues, and test in an isolated environment before production use. Stars and forks alone cannot answer these questions.
Source and freshness
Source: GitHub. Metadata observed 2026-10-22T12:12:53.932Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.