Emanuele Sabetta
Emanuele Sabetta
### Is your feature request related to a problem? Please describe. OpenInterpreter is amazing, but it a bit behind when it comes to the GUI/ComputerUse department. ### Describe the solution...
Please make a bookmarklet version of htmlarkdown.
Instrukt is very promising, especially the full textual UI! What it lacks is the ability to generate or edit code. Please add a coding copilot mode (like [Aider](https://github.com/Aider-AI/aider), but with...
Microsoft presented Omniparser V2 and it is showing the best performances in GUI parsing. You can read about the details [here](https://www.microsoft.com/en-us/research/articles/omniparser-v2-turning-any-llm-into-a-computer-use-agent/). It is not a multimodal but a visual parsing...
Currently Transformerlab only handles text. But the tendency for the future is converging towards Multimodal AI Models (MLLM). For example the recent Janus-Pro is a unified understanding and generation MLLM....
Microsoft presented Omniparser V2 and it is showing the best performances in GUI parsing. You can read about the details [here](https://www.microsoft.com/en-us/research/articles/omniparser-v2-turning-any-llm-into-a-computer-use-agent/). It is not a multimodal but a visual parsing...
Please add support for mlx-use https://github.com/browser-use/macOS-use
Currently the CTRL-C command (SIGINT) is often uneffective in a-Shell, because the keyboard input is often useless when a process is unresponsive. A 'Kill Process' button on the toolbar, equivalent...
PROBLEM: Currently Shellcheck cannot be used with modern AI IDE and Editors or CLI AI tools. The reason is that the text format of the output returns only 1 line...
Can you add a function to check if a file is a binary or a text?