qvac
QVAC - Local AI SDK and libraries for building private, cross-platform, peer-to-peer AI applications. Run LLMs, speech-to-text, translation, and more locally on
What is qvac?
QVAC - Local AI SDK and libraries for building private, cross-platform, peer-to-peer AI applications. Run LLMs, speech-to-text, translation, and more locally on Linux, macOS, Windows, Android, and iOS.
Overview of qvac
What it is
QVAC is a local AI SDK and model provider that lets you run a comprehensive range of AI workloads locally using open models across Linux, macOS, Windows, Android, and iOS. It provides an SDK for building local-first AI applications in JavaScript/TypeScript and Python, and an HTTP server with an OpenAI-compatible API for use as a local model provider.
Key features
- SDK for JavaScript/TypeScript and Python for building local-first AI applications.
- HTTP server with OpenAI-compatible API to connect AI tools such as OpenCode and OpenClaw.
- Local-first: run AI offline with inference optimized for commodity hardware.
- Privacy and control: keep data local, no cloud or third-party APIs required.
- Cross-platform: one codebase for Linux, macOS, Windows, Android, and iOS.
- Peer-to-peer: fetch AI models directly between peers.
Use cases
- Building mobile and desktop apps that run AI locally.
- Serving local models to favorite AI tools via an OpenAI-compatible API.
- Running LLMs, speech-to-text, translation, image/video generation, and more on any device without cloud dependencies.
Getting started
JavaScript quickstart:bashmkdir qvac-examplescd qvac-examplesnpm init -y && npm pkg set type=modulenpm i @qvac/sdkCreate qvac.config.json and quickstart.js as shown in the README, then run:bashQVAC_CONFIG_PATH=./qvac.config.json node quickstart.jsPython quickstart:bashmkdir qvac-examples-pycd qvac-examples-pypython -m venv .venvsource .venv/bin/activatepip install tetherto-qvac-sdk -f https://github.com/tetherto/qvac/releases/expanded_assets/sdk-vCreate quickstart.py as shown in the README, then run:bashpython quickstart.pyHTTP server quickstart:bashnpm install -g @qvac/climkdir qvac-server && cd qvac-serverCreate qvac.config.json with model configuration, then start the server:bashqvac serve openaiUse any OpenAI-compatible client to connect to http://localhost:11434/v1.
License and pricing
License: Apache-2.0. Pricing: open source (no pricing information provided).
Based on the project's public README and repository metadata.