self-operating-computer
self-operating-computer copied to clipboard
OthersideAI
A framework to enable multimodal models to operate a computer.
### Is your feature request related to a problem? Please describe. Currently, the self-operating-computer only supports direct API connections to specific AI providers. This limits flexibility for users who want...
## What does this PR do? Fixes # (issue) ## Requirement/Documentation - If there is a requirement document, please, share it here. ## Type of change - [ ] Bug...
## What does this PR do? Fixes # (issue) ## Requirement/Documentation - If there is a requirement document, please, share it here. ## Type of change - [ ] Bug...
selfjunk ## What does this PR do? Fixes # (issue) ## Requirement/Documentation - If there is a requirement document, please, share it here. ## Type of change - [ ]...
All is in title. But I suppose it's possible to combine multiples model. (LLM/Vision/Clip...)
Clicking doing nothing, ctrl v doing nothing? Is this a prank?
## What does this PR do? - Introduced handling for new models (`gpt-5-with-ocr`, `gpt-5-research-with-ocr`, `gpt-5-mini-with-ocr`, and `gpt-5-nano-with-ocr`) in `apis.py`. - Updated `config.py` to include the new models in validation. -...
- Added a new functionality to support Azure OpenAI models. especially for GPT 4 OCR model # How to use **prompt:** _operate --model gpt-4.1-with-ocr --verbose --prompt "open notepad, open new...
## If you are having issues installing: Like others have mentioned, installing with python3.11 will solve package installation errors ## If you have a Wayland Compositor: Essentially if gnome-shell's screenshot...
### Version v2.0.15 (Latest) Release Summary **New Features:** * **Centralized Model Management:** All model configurations are now managed in a single file (`operate/models/model_configs.py`), making it easier to add, remove, and...
Metadata
Owner
Metadata
A framework to enable multimodal models to operate a computer.