By name: gui-agent description: Control desktop GUI applications via screenshots and automated actions. homepage: https://github.com/bytedance/UI-TARS metadata: {"syll":{"emoji":"🖥️","requires":{"bins":[],"env":["SYLL__TOOLS__GUI__ENABLED"]}}}
GUI Agent
You can interact with desktop applications using the gui_action tool.
How It Works
- The tool captures a screenshot of the current screen
- Sends it to the UI-TARS vision model for analysis
- UI-TARS returns a thought + action (click, type, scroll, etc.)
- The action is executed via pyautogui
- Steps repeat until the task is complete or max steps reached
Usage Protocol
When the user asks you to perform a GUI task:
- Understand the goal - Break the task into clear steps
- Call
gui_actionwith a clear instruction - Review the result - Check the returned screenshot and status
- Iterate if needed - Call again with refined instructions
Example
User: "Open Chrome and search for 'Syll'"
You should call:
gui_action(instruction="Open Chrome browser, click on the address bar, type 'Syll' and press Enter")
Safety Rules
Never perform destructive actions without user confirmation:
- Deleting files or folders
- Closing unsaved documents
- System settings changes
- Financial transactions
- Sending messages/emails
Always verify the current screen state before acting
Stop immediately if the screen shows unexpected content (login pages with sensitive data, etc.)
Report clearly what actions were taken and their results
Supported Actions
| Action | Description | Example |
|---|---|---|
click |
Left click at position | click(point='<point>500 300</point>') |
right_click |
Right click | right_click(point='<point>500 300</point>') |
double_click |
Double click | double_click(point='<point>500 300</point>') |
drag |
Drag from A to B | drag(start='<point>100 100</point>', end='<point>200 200</point>') |
type |
Type text | type(content='hello world') |
hotkey |
Key combination | hotkey(key='ctrl+c') |
scroll |
Scroll up/down | scroll(point='<point>500 300</point>', direction='down', amount=3) |
wait |
Pause | wait(seconds=2) |
finished |
Task complete | finished(content='Done') |
Configuration
Enable in config.json:
{
"tools": {
"gui": {
"enabled": true,
"ui_tars": {
"api_base": "http://localhost:8000/v1",
"api_key": "your-key",
"model": "ui-tars"
},
"max_steps": 15,
"confirm_destructive": true
}
}
}