Idea: Selfhosted Interface for LLMs
-
wrote on last edited by [email protected]
Like SearchXNG but for chatbots.
Acts as a trusted inbetween that takes the hit on all the tracking for you and you need no account.
There would be a self-hosted server with a webinterface, where you can choose which of the popular chatbots or hosted open source models you want to ask.
The not free Accounts could be payed with donations maybe?
Basically like duck.ai but without a big company involved.
-
Like SearchXNG but for chatbots.
Acts as a trusted inbetween that takes the hit on all the tracking for you and you need no account.
There would be a self-hosted server with a webinterface, where you can choose which of the popular chatbots or hosted open source models you want to ask.
The not free Accounts could be payed with donations maybe?
Basically like duck.ai but without a big company involved.
Your goal is antithetical since even without tracking the LLM is still absorbing everything you say to it.
If you're concerned, just run a local LLM and skip the web service one.
-
Like SearchXNG but for chatbots.
Acts as a trusted inbetween that takes the hit on all the tracking for you and you need no account.
There would be a self-hosted server with a webinterface, where you can choose which of the popular chatbots or hosted open source models you want to ask.
The not free Accounts could be payed with donations maybe?
Basically like duck.ai but without a big company involved.
This is already a thing, there are a myriad of LLM chat interfaces where you can either connecting to models you are locally running or connect to APIs of providers. "Open WebUI", "librechat" and "Big-AGI" are web interfaces. On desktop you have things like jan.ai and a a lot more.
