Execute actions like mouse movements, clicks, keyboard input, and screenshots in the Bytebot desktop environment.
Request
The type of computer action to perform. Must be one of: move_mouse
, trace_mouse
,
click_mouse
, press_mouse
, drag_mouse
, scroll
, type_keys
, press_keys
,
type_text
, wait
, screenshot
, cursor_position
.
Mouse Actions
The target coordinates to move to.
Show coordinates properties
X coordinate (horizontal position)
Y coordinate (vertical position)
Example Request
Array of coordinate objects for the mouse path.
Keys to hold while moving the mouse along the path.
Example Request
The coordinates to click (uses current cursor position if omitted).
Show coordinates properties
X coordinate (horizontal position)
Y coordinate (vertical position)
Mouse button to click. Must be one of: left
, right
, middle
.
Number of clicks to perform. Default: 1
Keys to hold while clicking (e.g., [‘ctrl’, ‘shift’])
Example Request
The coordinates to press/release (uses current cursor position if omitted).
Show coordinates properties
X coordinate (horizontal position)
Y coordinate (vertical position)
Mouse button to press/release. Must be one of: left
, right
, middle
.
Whether to press or release the button. Must be one of: up
, down
.
Example Request
Array of coordinate objects for the drag path.
Mouse button to use for dragging. Must be one of: left
, right
, middle
.
Keys to hold while dragging.
Example Request
Keyboard Actions
Array of keys to type in sequence.
Delay between key presses in milliseconds.
Example Request
Array of keys to press or release.
Whether to press or release the keys. Must be one of: up
, down
.
Example Request
Delay between characters in milliseconds.
Example Request
System Actions
Wait duration in milliseconds.
Example Request
No parameters required.
Example Request
No parameters required.
Example Request
Response
Responses vary based on the action performed:
Default Response
Most actions return a simple success response:
Screenshot Response
Returns the screenshot as a base64 encoded string:
Cursor Position Response
Returns the current cursor position:
Error Response
Code Examples
curl -X POST http://localhost:9990/computer-use \
-H "Content-Type: application/json" \
-d '{"action": "move_mouse", "coordinates": {"x": 100, "y": 200}}'