**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.
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 schema](https://docs.trycua.com/docs/agent-sdk/message-format)
- 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))
- combine UI grounding models with any LLM using [composed agents](https://docs.trycua.com/docs/agent-sdk/supported-agents/composed-agents)
- use new UI agent models and UI grounding models from the Model Zoo below with just a model string (e.g., `ComputerAgent(model="openai/computer-use-preview")`)
- use API or local inference by changing a prefix (e.g., `openai/`, `openrouter/`, `ollama/`, `huggingface-local/`, `mlx/`, [etc.](https://docs.litellm.ai/docs/providers))
# Quick Start
- [Clone a starter template and run the code in <1 min](https://github.com/trycua/agent-template) (⭐️ Recommended!)
- [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)
# Agent Usage
```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
Cua uses the OpenAI Agent response format.
Example
```json
{
"output": [
{
"role": "user",
"content": "go to trycua on gh"
},
{
"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"
},
{
"type": "computer_call_output",
"call_id": "call_QI6OsYkXxl6Ww1KvyJc4LKKq",
"output": {
"type": "input_image",
"image_url": "data:image/png;base64,..."
}
},
{
"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
}
}
```
## Model Configuration
These are the valid model configurations for `ComputerAgent(model="...")`:
| Configuration | Description |
| ---------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------- |
| `{computer-use-model}` | A single model to perform all computer-use tasks |
| `{grounding-model}+{any-vlm-with-tools}` | [Composed](https://docs.trycua.com/docs/agent-sdk/supported-agents/composed-agents) with VLM for captioning and grounding LLM for element detection |
| `moondream3+{any-llm-with-tools}` | [Composed](https://docs.trycua.com/docs/agent-sdk/supported-agents/composed-agents) with Moondream3 for captioning and UI element detection |
| `human/human` | A [human-in-the-loop](https://docs.trycua.com/docs/agent-sdk/supported-agents/human-in-the-loop) in place of a model |
### Model Capabilities
The following table shows which capabilities are supported by each model:
| Model | Computer-Use | Grounding | Tools | VLM |
| -------------------------------------------------------------------------------------------------------------------------------- | :----------: | :-------: | :---: | :-: |
| [Claude Sonnet/Haiku](https://docs.claude.com/en/docs/agents-and-tools/tool-use/computer-use-tool#how-to-implement-computer-use) | ✓ | ✓ | ✓ | ✓ |
| [OpenAI CU Preview](https://platform.openai.com/docs/models/computer-use-preview) | ✓ | ✓ | | ✓ |
| [GLM-V](https://huggingface.co/THUDM/glm-4v-9b) | ✓ | ✓ | ✓ | ✓ |
| [Gemini CU Preview](https://ai.google.dev/gemini-api/docs/computer-use) | ✓ | ✓ | | ✓ |
| [InternVL](https://huggingface.co/OpenGVLab/InternVL3_5-1B) | ✓ | ✓ | ✓ | ✓ |
| [UI-TARS](https://huggingface.co/ByteDance-Seed/UI-TARS-1.5-7B) | ✓ | ✓ | ✓ | ✓ |
| [OpenCUA](https://huggingface.co/xlangai/OpenCUA-7B) | | ✓ | | |
| [GTA](https://huggingface.co/HelloKKMe/GTA1-7B) | | ✓ | | |
| [Holo](https://huggingface.co/Hcompany/Holo1.5-3B) | | ✓ | | |
| [Moondream](https://huggingface.co/moondream/moondream3-preview) | | ✓ | | |
| [OmniParser](https://github.com/microsoft/OmniParser) | | ✓ | | |
### Model IDs
Examples of valid model IDs
| Model | Model IDs |
| -------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------- |
| [Claude Sonnet/Haiku](https://docs.claude.com/en/docs/agents-and-tools/tool-use/computer-use-tool#how-to-implement-computer-use) | `anthropic/claude-sonnet-4-5`, `anthropic/claude-haiku-4-5` |
| [OpenAI CU Preview](https://platform.openai.com/docs/models/computer-use-preview) | `openai/computer-use-preview` |
| [GLM-V](https://huggingface.co/THUDM/glm-4v-9b) | `openrouter/z-ai/glm-4.5v`, `huggingface-local/zai-org/GLM-4.5V` |
| [Gemini CU Preview](https://ai.google.dev/gemini-api/docs/computer-use) | `gemini-2.5-computer-use-preview` |
| [InternVL](https://huggingface.co/OpenGVLab/InternVL3_5-1B) | `huggingface-local/OpenGVLab/InternVL3_5-{1B,2B,4B,8B,...}` |
| [UI-TARS](https://huggingface.co/ByteDance-Seed/UI-TARS-1.5-7B) | `huggingface-local/ByteDance-Seed/UI-TARS-1.5-7B` |
| [OpenCUA](https://huggingface.co/xlangai/OpenCUA-7B) | `huggingface-local/xlangai/OpenCUA-{7B,32B}` |
| [GTA](https://huggingface.co/HelloKKMe/GTA1-7B) | `huggingface-local/HelloKKMe/GTA1-{7B,32B,72B}` |
| [Holo](https://huggingface.co/Hcompany/Holo1.5-3B) | `huggingface-local/Hcompany/Holo1.5-{3B,7B,72B}` |
| [Moondream](https://huggingface.co/moondream/moondream3-preview) | `moondream3` |
| [OmniParser](https://github.com/microsoft/OmniParser) | `omniparser` |
Missing a model? Create 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)!
# Computer
```bash
pip install cua-computer[all]
```
```python
from computer import Computer
async with Computer(
os_type="linux",
provider_type="cloud",
name="your-sandbox-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!")
```
# 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)/[TS](./libs/typescript/computer/README.md))** | Interface for controlling virtual machines | `pip install "cua-computer[all]"` `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)/[TS](./libs/typescript/core/README.md))** | Core utilities | `pip install cua-core` `npm install @trycua/core` |
# Resources
- [Cua Blog](https://www.trycua.com/blog)
- [Cua Docs](https://docs.trycua.com)
# Community and Contributions
We welcome contributions to Cua! Please refer to our [Contributing Guidelines](CONTRIBUTING.md) for details.
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.md) file for details.
Portions of this project, specifically components adapted from Kasm Technologies Inc., are also licensed under the MIT License. See [libs/kasm/LICENSE](libs/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 the [OmniParser LICENSE](https://github.com/microsoft/OmniParser/blob/master/LICENSE) for details.
## Third-Party Licenses and Optional Components
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 via `pip install "cua-agent[omni]"`) installs the `cua-som` module, which includes `ultralytics` 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 for `ultralytics`).
## 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., Microsoft Corporation, or Kasm Technologies.
# Stargazers
Thank you to all our supporters!
[](https://starchart.cc/trycua/cua)
# Sponsors
Thank you to all our [GitHub Sponsors](https://github.com/sponsors/trycua)!
