This commit is contained in:
Dillon DuPont
2025-07-25 19:16:44 -04:00
parent d94879aade
commit 110f2e9223

View File

@@ -0,0 +1,92 @@
---
title: Quickstart (CLI)
description: Get started with the c/ua Agent CLI in 5 steps
icon: Rocket
---
Get up and running with the c/ua Agent CLI in 5 simple steps.
## 1. Introduction
c/ua combines Computer (interface) + Agent (AI) for automating desktop apps. The Agent CLI provides a clean terminal interface to control your remote computer using natural language commands.
## 2. Create Your First c/ua Container
1. Go to [trycua.com/signin](https://www.trycua.com/signin)
2. Navigate to **Dashboard > Containers > Create Instance**
3. Create a **Medium, Ubuntu 22** container
4. Note your container name and API key
## 3. Install c/ua
```bash
pip install "cua-agent[all]" cua-computer
```
## 4. Run the Agent CLI
Choose your preferred AI model and run the CLI:
### OpenAI Computer Use Preview
```bash
python -m agent.cli openai/computer-use-preview
```
### Anthropic Claude
```bash
python -m agent.cli anthropic/claude-3-5-sonnet-20241022
python -m agent.cli anthropic/claude-opus-4-20250514
python -m agent.cli anthropic/claude-sonnet-4-20250514
```
### Omniparser + LLMs
```bash
python -m agent.cli omniparser+anthropic/claude-3-5-sonnet-20241022
python -m agent.cli omniparser+openai/gpt-4o
python -m agent.cli omniparser+vertex_ai/gemini-pro
```
### Local Models
```bash
# Hugging Face models (local)
python -m agent.cli huggingface-local/ByteDance-Seed/UI-TARS-1.5-7B
# MLX models (Apple Silicon)
python -m agent.cli mlx/mlx-community/UI-TARS-1.5-7B-6bit
# Ollama models
python -m agent.cli omniparser+ollama_chat/llama3.2:latest
```
## 5. Interactive Setup
If you haven't set up environment variables, the CLI will guide you through the setup:
1. **Container Name**: Enter your c/ua container name (or get one at [trycua.com](https://www.trycua.com/))
2. **CUA API Key**: Enter your c/ua API key
3. **Provider API Key**: Enter your AI provider API key (OpenAI, Anthropic, etc.)
## 6. Start Chatting
Once connected, you'll see:
```
💻 Connected to your-container-name (model, agent_loop)
Type 'exit' to quit.
>
```
You can ask your agent to perform actions like:
- "Take a screenshot and tell me what's on the screen"
- "Open Firefox and go to github.com"
- "Type 'Hello world' into the terminal"
- "Close the current window"
- "Click on the search button"
---
For advanced Python usage and GUI interface, see the [Quickstart (GUI)](/docs/quickstart-ui) and [Quickstart for Developers](/docs/quickstart-devs).
For a complete list of supported models, see [Supported Agents](/docs/agent-sdk/supported-agents).
For running models locally, see [Running Models Locally](/docs/agent-sdk/local-models).