I love kagi but I don't think it actively filters out ai generated content.
I know when searching for pictures you can disable AI generated images.
I think the hard part for a search engine is that unless there is some kind of identifying mark on the content, how do they know that an ai didn't write a top 10 list of pastebin alternatives?
Sorry about that bad link. Here it is.
Install ollama
Download any uncensored llm
From ollama's library
Serve, Pull, and Run
From huggingface
download and any gguf model you want with uncensored in the name. I like ggufs from TheBloke
Create a GGUF file from a non gguf llm for ollama
setup python env
Install pyenv and then follow instructions to update .bashrc
Update pyenv and install a version of python you need
Create a virtual environment
Use the virtual environment and download the pre-reqs
Download the model from huggingface.
For this example, Im going to pull llama3.2_1b_2025_uncensored Note that this llm is 1B so can be ran on a low spec device.
Transpose HF to GGUF
Serve, Organize, Create, and Run