self-operating-computer icon indicating copy to clipboard operation
self-operating-computer copied to clipboard

A framework to enable multimodal models to operate a computer.

Results 130 self-operating-computer issues
Sort by recently updated
recently updated
newest added

## What does this PR do? Fixes # (issue) ## Requirement/Documentation - If there is a requirement document, please, share it here. ## Type of change - [ ] Bug...

Gemini 1.0 Pro Vision has been deprecated on July 12, 2024. Consider switching to different model, for example gemini-1.5-flash.

bug

I was wondering if you were considering to add support for the new GPT-4o-mini that would be awesome thanks

enhancement

# [FEATURE] Add the support of llava:38b ### Is your feature request related to a problem? Please describe. I’m always frustrated when I need to work with large language models...

enhancement

### Describe the bug I got the error No module named 'bidi.algorithm' when I installed via pip and ran the operate command. It installed 0.5.0 by default. Uninstalling that package...

bug

Please add support for more ollama multimodal models, such as llava:34b

enhancement

Hi, thank you for your open-source efforts, this repository is fantastic! I am currently using OCR + Segment Anything along with some simple algorithms to mark screenshots. Here is the...

Found a bug? Please fill out the sections below. šŸ‘ ### Describe the bug [Self-Operating Computer | claude-3] Hello, I can help you with anything. What would you like done?...

bug

After installing and configure the Openai API key in the intial dialog, I made a mistake with the code and now I can't change it. I've been searching for os...

bug

Hi, I have run the pip install on a Mac running Sonoma and that worked fine, but when typing "operate" it says zsh: command not found: operate I suspect this...

bug