Release2026-10-29

Tetherto released QVAC, an open-source SDK for running AI models on-device. It supports text, image, music, and video generation, speech-to-text, and peer-to-peer inference. The SDK works on Linux, macOS, Windows, Android, and iOS. It offers an HTTP server with an OpenAI-compatible API for integration with other tools. QVAC enables local-first AI applications with privacy and control. It also supports retrieval-augmented generation, fine-tuning, and multimodal tasks. Models can be fetched directly between peers. The project provides JavaScript/TypeScript and Python SDKs.

What it unlocks

Running AI models locally without cloud or API keys across multiple platforms.

What you need to act on it

  • local device with supported hardware
  • installation of QVAC SDK or CLI

Sources

Send this to someone who needs it

Shares the story and its sources. Nothing about you.

What does this mean for your job?

This is the story as everyone gets it. Once a week we send you the version written for your role — what changed, why it matters for the work you actually do, and one thing to try. Free while we tune it.