Tether has launched QVAC SDK, an open-source software development kit empowering developers to build, run, and fine-tune artificial intelligence directly on local devices across major operating systems.
Applications created with this toolkit can operate on iOS, Android, Windows, macOS, and Linux from a single codebase, eliminating reliance on cloud-only infrastructure.
The QVAC SDK is engineered to keep AI functions such as writing assistance, transcription, translation, image generation, search, and summarization running directly on consumer hardware, including smartphones and laptops. This approach promises improved privacy, lower latency, and continued functionality even with weak connectivity or offline servers.
At its core, QVAC Fabric, a fork of llama.cpp, supports text generation, embeddings, and multimodal workloads. The SDK also integrates whisper.cpp for speech-to-text and Bergamot for on-device translation, offering a unified interface that allows developers to combine capabilities without rewriting application logic.
Tether positions QVAC as its response to centralized AI, emphasizing private, local, and permissionless intelligence on any device. Previous initiatives include QVAC Genesis II, a synthetic educational dataset, and QVAC Health, a private AI health data hub.
Tether was reportedly in discussions to lead a €1 billion funding round in Neura Robotics, signaling a strategic push into the future of autonomous machines and AI agents.