inferit

inferit is a visual take on llm inference. Most inference frontends are limited to a single visual input/output "thread". This makes it hard to compare output from different models, prompts and sampler settings. inferit solves this with its UI that allows for an unlimited number of side-by-side generations. This makes it a perfect fit to compare and experiment with different models, prompts and sampler settings.

Some example use cases:

• model exploration and comparison
• prompt engineering
• sampler setting optimizations

Supported Backends:

• Any local or remote backend that is compatible with the OpenAI API
• Chrome's built-in llm (Gemini Nano)

run it

1. I've deployed an instance for instant access here: https://inferit.index.garden (online)
2. Same code also ships as browser extension to run local and offline w/o having to start a process: https://chromewebstore.google.com/detail/inferit/celkhcifjknihgjlieolcmchofdloagk
3. Run it locally from this repo:

   pnpm install
   pnpm build
   pnpm preview

once running, set your api creds in the settings (stored on your device, window.localStorage) and u are good to go

development

pnpm dev

Contributions of any kind are warmly welcomed!
<3