I’m confused as to why one would do this.
What in particular? Maybe I can tell you.
My initial use case was testing graphrag locally, which might become relevant at work later on, so I generalized the thing I did to get it working through an agent subscription. Actually that usage is public too: https://github.com/sebastiancarlos/graphrag-faaah
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?
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.
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.
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.
I think you lost most of us at “AI agent”.
Yeah, I don’t like agents either, so I’ll take it. This just solved a real problem I had, so I went ahead and shared it
It’s vibe-coded, eww.
It’s not, but some AI was used for the code. I think vibe coding it would have produced a very different (and larger) code base. What makes you think it’s vibe coded?
What makes you think it’s vibe coded?
“some” AI was used for the code.
Do you think rather than AI was used for most of the code? I don’t think it was.
If what you’re saying is that “vibe-coded” applies when “some AI was used”, and that it’s a bad thing, that’s a valid opinion that I might agree with in some contexts (like an ethical one).
So it’s a proxy? What’s the advantage of this? It implies you save money somehow, I think.
Yes. The idea is that you can have any tool on one side (which expects an OpenAI-like LLM API, which is a bit of a de facto standard), and any LLM on the other side (which can be an agent subscription).
I used this, for example, to test GraphRAG locally (which is designed to make a lot of LLM API calls) by piping it to an agent subscription I already had (and not needing to buy expensive API tokens for the low volume I needed).
So it’s an adapter. I see.
Lots of hate here for computing tools. I don’t think I have a use case for this, personally, but it’s nice to see a creative solution to modern problems.
Thanks!
