cua

<div align="center"> <picture> <source media="(prefers-color-scheme: dark)" alt="Cua logo" height="150" srcset="img/logo_white.png"> <source media="(prefers-color-scheme: light)" alt="Cua logo" height="150" srcset="img/logo_black.png"> <img alt="Cua logo" height="150" src="img/logo_black.png"> </picture> [](#) [](#) [](#) [](https://discord.com/invite/mVnXXpdE85) <br> <a href="https://trendshift.io/repositories/13685" target="_blank"><img src="https://trendshift.io/api/badge/repositories/13685" alt="trycua%2Fcua | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a> </div> **cua** ("koo-ah") is Docker for [Computer-Use Agents](https://www.oneusefulthing.org/p/when-you-give-a-claude-a-mouse) - it enables AI agents to control full operating systems in virtual containers and deploy them locally or to the cloud. <div align="center"> <video src="https://github.com/user-attachments/assets/c619b4ea-bb8e-4382-860e-f3757e36af20" width="600" controls></video> </div> With the Computer SDK, you can: - automate Windows, Linux, and macOS VMs with a consistent, [pyautogui-like API](https://docs.trycua.com/docs/libraries/computer#interface-actions) - create & manage VMs [locally](https://docs.trycua.com/docs/computer-sdk/computers#cua-local-containers) or using [cua cloud](https://www.trycua.com/) With the Agent SDK, you can: - run computer-use models with a [consistent output](https://docs.trycua.com/docs/agent-sdk/chat-history#message-array-structure) - run composed agents using UI grounding models and any LLM - use any liteLLM provider (`openai/`, `openrouter/`, etc.) or our included local providers (`huggingface-local/`, `mlx/`) - quickly evaluate new UI agent models and UI grounding models - `anthropic/claude-opus-4-1-20250805` (using [Computer-Use Models](https://docs.trycua.com/docs/agent-sdk/supported-agents/computer-use-agents)) - `openai/computer-use-preview` - `openrouter/z-ai/glm-4.5v` - `huggingface-local/ByteDance-Seed/UI-TARS-1.5-7B` - `omniparser+{any LLM}` (using [Composed Agents](https://docs.trycua.com/docs/agent-sdk/supported-agents/composed-agents)) - `huggingface-local/HelloKKMe/GTA1-7B+{any LLM}` - `huggingface/HelloKKMe/GTA1-32B+{any LLM}` - `vllm_hosted/HelloKKMe/GTA1-72B+{any LLM}` - `human/human` (using [Human-in-the-Loop](https://docs.trycua.com/docs/agent-sdk/supported-agents/human-in-the-loop)) - benchmark on OSWorld-Verified, SheetBench-V2, and more [with a single line of code using HUD](https://docs.trycua.com/docs/agent-sdk/integrations/hud) ([Notebook](https://github.com/trycua/cua/blob/main/notebooks/eval_osworld.ipynb)) Missing a model? [Raise a feature request](https://github.com/trycua/cua/issues/new?assignees=&labels=enhancement&projects=&title=%5BAgent%5D%3A+Add+model+support+for+) or [contribute](https://github.com/trycua/cua/blob/main/CONTRIBUTING.md)! <br/> # Quick Start - [Get started with a Computer-Use Agent UI](https://docs.trycua.com/docs/quickstart-ui) - [Get started with the Computer-Use Agent CLI](https://docs.trycua.com/docs/quickstart-cli) - [Get Started with the Python SDKs](https://docs.trycua.com/docs/quickstart-devs) <br/> # Usage ([Docs](https://docs.trycua.com/docs)) ```bash pip install cua-agent[all] ``` ```python from agent import ComputerAgent agent = ComputerAgent( model="anthropic/claude-3-5-sonnet-20241022", tools=[computer], max_trajectory_budget=5.0 ) messages = [{"role": "user", "content": "Take a screenshot and tell me what you see"}] async for result in agent.run(messages): for item in result["output"]: if item["type"] == "message": print(item["content"][0]["text"]) ``` ### Output format (OpenAI Agent Responses Format): ```json { "output": [ # user input { "role": "user", "content": "go to trycua on gh" }, # first agent turn adds the model output to the history { "summary": [ { "text": "Searching Firefox for Trycua GitHub", "type": "summary_text" } ], "type": "reasoning" }, { "action": { "text": "Trycua GitHub", "type": "type" }, "call_id": "call_QI6OsYkXxl6Ww1KvyJc4LKKq", "status": "completed", "type": "computer_call" }, # second agent turn adds the computer output to the history { "type": "computer_call_output", "call_id": "call_QI6OsYkXxl6Ww1KvyJc4LKKq", "output": { "type": "input_image", "image_url": "data:image/png;base64,..." } }, # final agent turn adds the agent output text to the history { "type": "message", "role": "assistant", "content": [ { "text": "Success! The Trycua GitHub page has been opened.", "type": "output_text" } ] } ], "usage": { "prompt_tokens": 150, "completion_tokens": 75, "total_tokens": 225, "response_cost": 0.01, } } ``` # Computer ([Docs](https://docs.trycua.com/docs/computer-sdk/computers)) ```bash pip install cua-computer[all] ``` ```python from computer import Computer async with Computer( os_type="linux", provider_type="cloud", name="your-container-name", api_key="your-api-key" ) as computer: # Take screenshot screenshot = await computer.interface.screenshot() # Click and type await computer.interface.left_click(100, 100) await computer.interface.type("Hello!") ``` # Resources - [How to use the MCP Server with Claude Desktop or other MCP clients](./libs/python/mcp-server/README.md) - One of the easiest ways to get started with Cua - [How to use OpenAI Computer-Use, Anthropic, OmniParser, or UI-TARS for your Computer-Use Agent](./libs/python/agent/README.md) - [How to use Lume CLI for managing desktops](./libs/lume/README.md) - [Training Computer-Use Models: Collecting Human Trajectories with Cua (Part 1)](https://www.trycua.com/blog/training-computer-use-models-trajectories-1) ## Modules | Module | Description | Installation | |--------|-------------|---------------| | [**Lume**](./libs/lume/README.md) | VM management for macOS/Linux using Apple's Virtualization.Framework | `curl -fsSL https://raw.githubusercontent.com/trycua/cua/main/libs/lume/scripts/install.sh \| bash` | | [**Lumier**](./libs/lumier/README.md) | Docker interface for macOS and Linux VMs | `docker pull trycua/lumier:latest` | | [**Computer (Python)**](./libs/python/computer/README.md) | Python Interface for controlling virtual machines | `pip install "cua-computer[all]"` | | [**Computer (Typescript)**](./libs/typescript/computer/README.md) | Typescript Interface for controlling virtual machines | `npm install @trycua/computer` | | [**Agent**](./libs/python/agent/README.md) | AI agent framework for automating tasks | `pip install "cua-agent[all]"` | | [**MCP Server**](./libs/python/mcp-server/README.md) | MCP server for using CUA with Claude Desktop | `pip install cua-mcp-server` | | [**SOM**](./libs/python/som/README.md) | Self-of-Mark library for Agent | `pip install cua-som` | | [**Computer Server**](./libs/python/computer-server/README.md) | Server component for Computer | `pip install cua-computer-server` | | [**Core (Python)**](./libs/python/core/README.md) | Python Core utilities | `pip install cua-core` | | [**Core (Typescript)**](./libs/typescript/core/README.md) | Typescript Core utilities | `npm install @trycua/core` | ## Community Join our [Discord community](https://discord.com/invite/mVnXXpdE85) to discuss ideas, get assistance, or share your demos! ## License Cua is open-sourced under the MIT License - see the [LICENSE](LICENSE) file for details. Microsoft's OmniParser, which is used in this project, is licensed under the Creative Commons Attribution 4.0 International License (CC-BY-4.0) - see the [OmniParser LICENSE](https://github.com/microsoft/OmniParser/blob/master/LICENSE) file for details. ## Contributing We welcome contributions to CUA! Please refer to our [Contributing Guidelines](CONTRIBUTING.md) for details. ## Trademarks Apple, macOS, and Apple Silicon are trademarks of Apple Inc. Ubuntu and Canonical are registered trademarks of Canonical Ltd. Microsoft is a registered trademark of Microsoft Corporation. This project is not affiliated with, endorsed by, or sponsored by Apple Inc., Canonical Ltd., or Microsoft Corporation. ## Stargazers Thank you to all our supporters! [](https://starchart.cc/trycua/cua) ## Contributors <!-- ALL-CONTRIBUTORS-LIST:START - Do not remove or modify this section --> <!-- prettier-ignore-start --> <!-- markdownlint-disable --> <table> <tbody> <tr> <td align="center" valign="top" width="14.28%"><a href="https://github.com/f-trycua"><img src="https://avatars.githubusercontent.com/u/195596869?v=4?s=100" width="100px;" alt="f-trycua"/><br />_{<b>f-trycua</b>}</a><br /><a href="#code-f-trycua" title="Code">💻</a></td> <td align="center" valign="top" width="14.28%"><a href="http://pepicrft.me"><img src="https://avatars.githubusercontent.com/u/663605?v=4?s=100" width="100px;" alt="Pedro Piñera Buendía"/><br />_{<b>Pedro Piñera Buendía</b>}</a><br /><a href="#code-pepicrft" title="Code">💻</a></td> <td align="center" valign="top" width="14.28%"><a href="https://iamit.in"><img src="https://avatars.githubusercontent.com/u/5647941?v=4?s=100" width="100px;" alt="Amit Kumar"/><br />_{<b>Amit Kumar</b>}</a><br /><a href="#code-aktech" title="Code">💻</a></td> <td align="center" valign="top" width="14.28%"><a href="https://productsway.com/"><img src="https://avatars.githubusercontent.com/u/870029?v=4?s=100" width="100px;" alt="Dung Duc Huynh (Kaka)"/><br />_{<b>Dung Duc Huynh (Kaka)</b>}</a><br /><a href="#code-jellydn" title="Code">💻</a></td> <td align="center" valign="top" width="14.28%"><a href="http://zaydkrunz.com"><img src="https://avatars.githubusercontent.com/u/70227235?v=4?s=100" width="100px;" alt="Zayd Krunz"/><br />_{<b>Zayd Krunz</b>}</a><br /><a href="#code-ShrootBuck" title="Code">💻</a></td> <td align="center" valign="top" width="14.28%"><a href="https://github.com/PrashantRaj18198"><img src="https://avatars.githubusercontent.com/u/23168997?v=4?s=100" width="100px;" alt="Prashant Raj"/><br />_{<b>Prashant Raj</b>}</a><br /><a href="#code-PrashantRaj18198" title="Code">💻</a></td> <td align="center" valign="top" width="14.28%"><a href="https://www.mobile.dev"><img src="https://avatars.githubusercontent.com/u/847683?v=4?s=100" width="100px;" alt="Leland Takamine"/><br />_{<b>Leland Takamine</b>}</a><br /><a href="#code-Leland-Takamine" title="Code">💻</a></td> </tr> <tr> <td align="center" valign="top" width="14.28%"><a href="https://github.com/ddupont808"><img src="https://avatars.githubusercontent.com/u/3820588?v=4?s=100" width="100px;" alt="ddupont"/><br />_{<b>ddupont</b>}</a><br /><a href="#code-ddupont808" title="Code">💻</a></td> <td align="center" valign="top" width="14.28%"><a href="https://github.com/Lizzard1123"><img src="https://avatars.githubusercontent.com/u/46036335?v=4?s=100" width="100px;" alt="Ethan Gutierrez"/><br />_{<b>Ethan Gutierrez</b>}</a><br /><a href="#code-Lizzard1123" title="Code">💻</a></td> <td align="center" valign="top" width="14.28%"><a href="https://ricterz.me"><img src="https://avatars.githubusercontent.com/u/5282759?v=4?s=100" width="100px;" alt="Ricter Zheng"/><br />_{<b>Ricter Zheng</b>}</a><br /><a href="#code-RicterZ" title="Code">💻</a></td> <td align="center" valign="top" width="14.28%"><a href="https://www.trytruffle.ai/"><img src="https://avatars.githubusercontent.com/u/50844303?v=4?s=100" width="100px;" alt="Rahul Karajgikar"/><br />_{<b>Rahul Karajgikar</b>}</a><br /><a href="#code-rahulkarajgikar" title="Code">💻</a></td> <td align="center" valign="top" width="14.28%"><a href="https://github.com/trospix"><img src="https://avatars.githubusercontent.com/u/81363696?v=4?s=100" width="100px;" alt="trospix"/><br />_{<b>trospix</b>}</a><br /><a href="#code-trospix" title="Code">💻</a></td> <td align="center" valign="top" width="14.28%"><a href="https://github.com/evnsnclr"><img src="https://avatars.githubusercontent.com/u/139897548?v=4?s=100" width="100px;" alt="Evan smith"/><br />_{<b>Evan smith</b>}</a><br /><a href="#code-evnsnclr" title="Code">💻</a></td> </tr> </tbody> </table> <!-- markdownlint-restore --> <!-- prettier-ignore-end --> <!-- ALL-CONTRIBUTORS-LIST:END -->