Skip to content

Releases: askui/vision-agent

v0.1.11

20 Dec 13:17
Compare
Choose a tag to compare

What's Changed

New Contributors

Full Changelog: v0.1.9...v0.1.11

Reporting

03 Dec 10:59
Compare
Choose a tag to compare
  • Feature to generate HTML report of an automation run

Integrate ShowUI HF Model

28 Nov 09:26
Compare
Choose a tag to compare
  • showlab/ShowUI-2B now available as click model via HF Spaces

Hugging Face Integration

25 Nov 17:02
Compare
Choose a tag to compare
  • Integrate Hugging Face Spaces models for click command

Bugfixes

22 Nov 16:03
Compare
Choose a tag to compare
  • add missing requests dependency
  • fix agent.keyboard and add type hints for keyboard commands

AskUI Integration

21 Nov 13:14
Compare
Choose a tag to compare
  • Integrates with AskUI as a model provider
  • Adds AskUI PTA and OCR models
  • Adds model routing to execute click commands with different models from different model providers
  • Checks token availability for model providers and raises AutomationError on missing auth

Direct Tool Use Docs and Clipboard

15 Nov 13:43
Compare
Choose a tag to compare
  • integrated pyperclip for clipboard access
  • agent os controlls now behind tools interface agent.tools.os...
  • improved docs on tools

Keyboard Fixes

14 Nov 12:58
Compare
Choose a tag to compare
  • Map keysym key names to agent os names -> fixes issues with keyboard use in act()

Toolbox and Bugfixes

06 Nov 12:31
Compare
Choose a tag to compare
  • Move tools like webbrowser under a tools attribute (breaking change)
  • improved docs
  • disable default debugDraw flag

Improved Logging and Display Selection Fixes

05 Nov 15:14
Compare
Choose a tag to compare
  • Improved logging for Agent activity
  • Set default log_level to INFO
  • Improved Readme for installation and added Wayland warning
  • Fixes for display selection