Repository files navigation

We’re hosting theComputer-Use Agents SOTA Challenge atHack the North and online!

Track A (On-site @ UWaterloo): Reserved for participants accepted to Hack the North. 🏆 Prize:YC interview guaranteed.
Track B (Remote): Open to everyone worldwide. 🏆 Prize:Cash award.

👉 Sign up here:trycua.com/hackathon

cua ("koo-ah") is Docker forComputer-Use Agents - it enables AI agents to control full operating systems in virtual containers and deploy them locally or to the cloud.

With the Computer SDK, you can:

• automate Windows, Linux, and macOS VMs with a consistent,pyautogui-like API
• create & manage VMslocally or usingcua cloud

With the Agent SDK, you can:

• run computer-use models with aconsistent output
• 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 (usingComputer-Use Models)
  • openai/computer-use-preview
  • openrouter/z-ai/glm-4.5v
  • huggingface-local/ByteDance-Seed/UI-TARS-1.5-7B
  • omniparser+{any LLM} (usingComposed Agents)
  • huggingface-local/HelloKKMe/GTA1-7B+{any LLM}
  • huggingface/HelloKKMe/GTA1-32B+{any LLM}
  • vllm_hosted/HelloKKMe/GTA1-72B+{any LLM}
  • human/human (usingHuman-in-the-Loop)
• benchmark on OSWorld-Verified, SheetBench-V2, and morewith a single line of code using HUD (Notebook)

Missing a model?Raise a feature request orcontribute!

• Get started with a Computer-Use Agent UI
• Get started with the Computer-Use Agent CLI
• Get started with the Python SDKs

pip install cua-agent[all]

fromagentimportComputerAgentagent=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"}]asyncforresultinagent.run(messages):foriteminresult["output"]:ifitem["type"]=="message":print(item["content"][0]["text"])

{"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,  }}

pip install cua-computer[all]

fromcomputerimportComputerasyncwithComputer(os_type="linux",provider_type="cloud",name="your-container-name",api_key="your-api-key")ascomputer:# Take screenshotscreenshot=awaitcomputer.interface.screenshot()# Click and typeawaitcomputer.interface.left_click(100,100)awaitcomputer.interface.type("Hello!")

• How to use the MCP Server with Claude Desktop or other MCP clients - 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
• How to use Lume CLI for managing desktops
• Training Computer-Use Models: Collecting Human Trajectories with Cua (Part 1)

Join ourDiscord community to discuss ideas, get assistance, or share your demos!

Cua is open-sourced under the MIT License - see theLICENSE file for details.

Portions of this project, specifically components adapted from Kasm Technologies Inc., are also licensed under the MIT License. Seelibs/kasm/LICENSE 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 theOmniParser LICENSE for details.

Some optional extras for this project depend on third-party packages that are licensed under terms different from the MIT License.

• The optional "omni" extra (installed viapip install "cua-agent[omni]") installs thecua-som module, which includesultralytics and is licensed under the AGPL-3.0.

When you choose to install and use such optional extras, your use, modification, and distribution of those third-party components are governed by their respective licenses (e.g., AGPL-3.0 forultralytics).

We welcome contributions to Cua! Please refer to ourContributing Guidelines for details.

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., Microsoft Corporation, or Kasm Technologies.

Thank you to all our supporters!

f-trycua 💻	Pedro Piñera Buendía 💻	Amit Kumar 💻	Dung Duc Huynh (Kaka) 💻	Zayd Krunz 💻	Prashant Raj 💻	Leland Takamine 💻
ddupont 💻	Ethan Gutierrez 💻	Ricter Zheng 💻	Rahul Karajgikar 💻	trospix 💻	Evan smith 💻