mirror of
https://github.com/hanzoai/python-sdk.git
synced 2026-10-23 20:23:00 +00:00
zeekay
44e505abf2
- Add window management: get_active_window, list_windows, focus_window - Add screen management: get_screens, screen_size, current_screen - Add region abstractions: define_region, region_screenshot, region_locate - Add image utilities: locate_all, wait_for_image, wait_while_image - Add pixel operations: pixel, pixel_matches with tolerance - Add timing controls: set_pause, set_failsafe, countdown - Add input helpers: write (with clear), key_down/key_up, move_relative - Add batch operations: run multiple actions in one call - Performance: thread pool executor, cached screen info, faster polling - All operations non-blocking with async-first design
hanzo-tools-computer
Computer control tools for Hanzo AI - pyautogui-based Mac automation.
Installation
pip install hanzo-tools-computer
Usage
from hanzo_tools.computer import ComputerTool, register_tools
# Register with MCP server
register_tools(mcp_server, permission_manager)
Actions
Mouse
click- Click at (x, y)double_click- Double click at (x, y)right_click- Right click at (x, y)move- Move mouse to (x, y)drag- Drag to (x, y)scroll- Scroll by amount
Keyboard
type- Type text stringpress- Press single keyhotkey- Press key combination
Screen
screenshot- Capture screenlocate- Find image on screeninfo- Get screen/mouse info
Examples
# Click at coordinates
computer(action="click", x=100, y=200)
# Type text
computer(action="type", text="Hello world")
# Keyboard shortcut (Cmd+C on Mac)
computer(action="hotkey", keys=["command", "c"])
# Take screenshot
computer(action="screenshot")
# Get screen info
computer(action="info")
Safety
- FAILSAFE enabled: Move mouse to corner to abort
- macOS only (checks platform)
- All actions run in executor threads (non-blocking)
License
MIT