A friendly parrot that runs open source AI models on your PC — offline, and happy on as little as 8 GB of RAM.

Chat with any GGUF model, fully offline — your words never leave the room.

Tell it how to behave once, and it plays along in every message.
What happens on your PC stays on your PC. No accounts, no cloud, no sneaky telemetry.
Happy on modest hardware — from 8 GB of RAM up, depending on the model you throw at it.
A Go core wrapped around llama.cpp does the heavy lifting, right on Windows.
Load GGUF models like Qwen or Llama, and swap them whenever the mood strikes.
Dial replies up or down by choosing how many tokens the model gets to use.
Three things, one folder. Drop your models into models, keep llama.cpp next door, and double-click Kulasisi.exe. That's the whole setup.