Back to directory

NeveAI

A local AI orchestration platform for running large language models offline, with a FastAPI backend and a SvelteKit interface for chat, document work and task automation.

NeveAI

NeveAI is a local AI ecosystem designed to run large language models offline, without a subscription or external API. It lets a user chat with models, work with documents, automate tasks and generate images, with everything processed on the user's own computer.

The system combines an asynchronous FastAPI backend with a SvelteKit 5 frontend, an SQLite database managed through SQLAlchemy and Alembic, and the llama.cpp engine for GGUF models, with GPU acceleration through CUDA or Vulkan. An installer detects the GPU, downloads a matching llama.cpp build, creates a Python virtual environment, installs dependencies, builds the frontend and creates the needed folders and configuration.

It targets Windows as its primary platform, with Linux and macOS support requiring manual adaptation.

More in Inference

See all 770
  • OpenDecision

    deepanwadhwa.github.io

    An open-source Python package that answers typed questions about application state or documents using a local natural-language-inference model, returning structured choice, score, yes/no or evidence-relation values instead of free text.

  • Lifeboat

    iterate.ai

    A local inference server that puts an OpenAI- and Anthropic-compatible API in front of open-weight language models running on hardware you control, from a laptop to a GPU cluster.

  • Claude S40

    github.com

    An unofficial Claude chat client for 2007-era Nokia Series 40 phones, built as a Java ME app plus a small Go relay server, with web search, reading mode and saved chats.