Tether has unveiled the QVAC SDK, a toolkit designed for developing and deploying artificial intelligence directly on user devices.

Tether Launches QVAC SDK as the AI Universal Building Block that Runs, Trains, and Evolves Intelligence Across any Device and Platform
Learn more: https://t.co/n7mkjkD8cz

— Tether (@tether) April 9, 2026

According to the company, this open-source software kit allows for the creation and retraining of AI models on devices of all types—from smartphones to servers—without relying on cloud infrastructure.

Solutions built with the SDK can operate on iOS, Android, Windows, macOS, and Linux using a single codebase, eliminating the need for adaptation to specific operating environments.

Decentralizing AI

The company introduced the QVAC platform for decentralized artificial intelligence in May 2025. Tether noted that the current centralized AI model is not scalable due to latency, infrastructure vulnerabilities, and concentration of control.

As an alternative, the company proposed a concept of local deployment, where computations occur on the user's device, and data is not sent to external servers.

This approach aims to provide:

  • higher privacy levels;
  • lower latency;
  • resilience to failures and lack of internet connectivity.

“Applications based on QVAC continue to function even under low connectivity, making AI more practical in real-world scenarios. If the internet goes down or a server farm fails, nothing changes for the user,” the developers explained.

Technical Architecture

The SDK is built on QVAC Fabric—a modified minimalist engine, llama.cpp, for running local models. It fully supports the Llama ecosystem for text generation, embedding, and multimodal workloads.

The platform also integrates several autonomous mechanisms like Parakeet (speech recognition) and Bergamot (translation). These are unified under a single API, allowing developers to combine functions without altering application logic.

The QVAC SDK includes built-in P2P interaction mechanisms based on the Holepunch stack, enabling:

  • model distribution without centralized servers;
  • the use and future training of AI in a distributed network.

Tether positions the QVAC SDK as a foundational element for a new class of applications—from personal AI assistants to autonomous agents integrated with Web3 services.

“The world is approaching a point where billions of people will share the planet with billions of autonomous machines and trillions of AI agents. The current structure, where every decision is made through a centralized server, will not scale to meet this reality,” stated Tether CEO Paolo Ardoino.

Recall that in December 2025, the QVAC team released an open dataset for AI training.