• Jakeroxs@sh.itjust.works
      link
      fedilink
      arrow-up
      8
      ·
      2 days ago

      What’s the advantage/point vs just using an extension like Kilo or similar? What “reuse” is possible by saving the prompt/responses via text file?

      • sebastiancarlos@lemmy.sdf.orgOP
        link
        fedilink
        arrow-up
        4
        ·
        2 days ago

        Well, the main reason why I post my projects is for people to tell me what alternatives I’m missing, so thanks for that.

        I’m actually not that familiar with Kilo, but I believe it’s an agent/IDE-extension, and that you can use different providers for it, including coding agents (I think this is what you were referring to.)

        So basically my use case is more niche. I just had an external tool (Graphrag) that only worked with an LLM API, and I had just an agent subscription, so i built an agnostic protocol via the filesystem to make them work together.

        It’s agnostic because you can have any tool on one side (which expects an OpenAI-like LLM API), and any LLM on the other side (which can be an agent subscription).

        Nothing in Kilo would have allowed me to get Graphrag working, I think.

        • Jakeroxs@sh.itjust.works
          link
          fedilink
          arrow-up
          2
          ·
          1 day ago

          So how does it connect to any LLM without using their API?

          Yes though Kilo was my example since they built a lot of support for other providers, though coding specific of course.

          • sebastiancarlos@lemmy.sdf.orgOP
            link
            fedilink
            arrow-up
            1
            ·
            23 hours ago

            So how does it connect to any LLM without using their API?

            Well, the typical use would be by local Agent subscription. But in theory any LLM could work, so long as it’s made to follow the filesystem protocol that faaah expects.

            There’s a video in the repo with an example of how it works, plus a diagram.