Newelle is a GTK graphical front end for interacting with LLMs from Gnome desktop. It supports both local LLMs and online ones.

In addition to basic chat, it supports:

  • Speech to text and TTS models
  • Can perform web searches
  • Can drag files into Newelle to discuss it’s contents
  • Run terminal commands
  • Manage files
  • Other features like image generation can be added through it’s plugin system.

Obviously you’ll want to be careful with letting it interact with your system directly through files/terminal commands, but still sounds pretty promising.

    • vermaterc@lemmy.ml
      link
      fedilink
      English
      arrow-up
      4
      ·
      9 days ago

      I don’t need an AI to wipe my databases.

      A few things to note:

      1. What a moron runs LLM model to manage production database?
      2. Newelle seem to run commands in virtualized environment and asks user every time it runs any command. So you are 100% aware of what happens. You might as well run rm -rf * by hand by accident.
    • Fubarberry@sopuli.xyzOPM
      link
      fedilink
      English
      arrow-up
      3
      ·
      9 days ago

      I’ve tried Gemini-CLI, and while it can run terminal commands, it asks permission before each one. Being able to read the commands and then click yes once I see what it’s doing can work pretty well in my experience, and should be somewhat safe.

      They do recommend running gemini-cli inside a container though, for added safety. I’m not sure if that’s possible with Newelle yet.

      • pinball_wizard@lemmy.zip
        link
        fedilink
        English
        arrow-up
        1
        ·
        8 days ago

        I’ve tried Gemini-CLI, and while it can run terminal commands, it asks permission before each one.

        That sounds much safer.

        • Fubarberry@sopuli.xyzOPM
          link
          fedilink
          English
          arrow-up
          2
          ·
          8 days ago

          Having now spent some time with Newelle, it asks for permission before running commands as well. By default the commands are run inside the flatpak sandbox as well. It even gives the option to run the commands in an external window and see the results before deciding whether to let the LLM access the results of the command (in case you’re worried the results might have private info you don’t want shared.

          Overall it handles it really well to be honest.

  • vermaterc@lemmy.ml
    link
    fedilink
    English
    arrow-up
    2
    ·
    9 days ago

    Wow, I’ve just tried it and it’s really solid. Lightweight, feature rich (RAG, voice input, command virtualization, custom extensions), interface is just clean… I don’t think other platforms have an alternative that can compete with that for now, which is not an usual situation in terms of GUI software on Linux. Good job

  • Sims@lemmy.ml
    link
    fedilink
    English
    arrow-up
    1
    ·
    8 days ago

    Great. We need open alternatives/integration before the Corp monkeys saturates services/tools and the whole AI ecosystem. I don’t want to rely on corps and their services, and I don’t want to loose the AI capabilities. AI can help me de-google/de-westernize my life - max FLOSS and open living as possible.