Tether Launches QVAC SDK to Build On-Device AI Apps Without Cloud Servers

Stablecoin Giant Tether Launches Toolkit for Building Local, Offline AI Apps - Decrypt

CEO Paolo Ardoino positioned the move as preparation for a world with "billions of autonomous machines and trillions of AI agents." Tether, the company behind the world's largest stablecoin, USDT, announced the launch of QVAC SDK -- a fully open-source software development kit designed to run artificial intelligence applications directly on any device without requiring cloud servers. The cross-platform toolkit works unchanged across iOS, Android, Windows, macOS, and Linux environments, the company said. The SDK is built on QVAC Fabric, a fork of llama.cpp, providing compatibility with the llama.cpp model ecosystem for text generation, embeddings, and multimodal workloads. Through a single interface, developers can access text completion, embeddings, vision, optical character recognition, text-to-speech, speech-to-text, and translation capabilities. The toolkit's peer-to-peer functionality, powered by the Holepunch stack, enables decentralized model distribution and delegated inference. The company plans to add peer-to-peer swarms for decentralized training, fine-tuning, and inference in future updates. "The world is approaching a moment where billions of humans share the planet with billions of autonomous machines and trillions of AI agents," Tether CEO Paolo Ardoino said, in a statement. "The current model, routing every decision through a centralized server, won't scale to meet that reality." "The laws of physics alone make centralized AI a dead end: speed-of-light latency, single points of failure, and concentration of control are features of a system designed for a smaller world," he added. "QVAC is built for the world that's coming. It is the building block of the Stable Intelligence Era." The SDK emerges from QVAC, Tether Data's AI research initiative focused on building open, decentralized, and adaptive intelligence systems. The company has committed to substantial investments to expand QVAC's open-source ecosystem over the coming months and years, including specialized toolkits for robotics and brain-computer interfaces. The launch marks a significant strategic expansion for Tether beyond its core stablecoin business, positioning the company to compete with centralized AI providers by offering privacy-focused alternatives that process data locally rather than transmitting it to cloud servers.

Tether launches open-source on-device AI framework for developers - SiliconANGLE

Tether launches open-source on-device AI framework for developers Tether Operations S.A. de C.V., a company best known for operating and issuing the cryptocurrency of the same name, today announced the release of a fully open-source framework for developers to build artificial intelligence features directly onto devices and platforms. The framework is called the QVAC software development kit, which stands for QuantumVerse Automatic Computer. It comes from the company's QVAC unit, which says the company is building the foundation of a new AI internet designed to pave the way towards the "stable intelligence era" and handle the upcoming expansion of AI. "The world is approaching a moment where billions of humans share the planet with billions of autonomous machines and trillions of AI agents," Chief Executive Paolo Ardoino said. "The current model, routing every decision through a centralized server, won't scale to meet that reality. The laws of physics alone make centralized AI a dead end." QVAC is designed to remain abstract and run anywhere, on any device or platform, and operating system. Applications built on the SDK can run unchanged across iOS, Android, Windows, macOS and Linux. For consumers, this means they get access to the familiar AI features of text chat, summarization, email reading and reply, image generation, voice chat and more. For developers, the SDK simplifies creating applications that can be built once and run anywhere rather than managing a different source implementation for each platform, hardware specification and operating system. The company said the SDK integrates QVAC Fabric, a fork of llama.cpp, a popular runner for large language models, providing a framework to execute AI model workloads, embeddings, text generation, images, audio and video. It also builds in best-in-class local engines, including whisper.cpp and Parakeet for speech-to-text and Bergamot for on-device translation. Of course, Tether hails from a decentralized blockchain background, so built deeply into the core of the SDK is peer-to-peer functionality. QVAC includes built-in primitives for decentralized model distribution, allowing for delegated inference without the need for centralized infrastructure. This means that if any one peer, or outside node, goes down, the group of others can take up the slack and the AI cloud "brain" keeps running. The company added that soon, peer-to-peer swarms for decentralized training, fine-tuning and inference will come online. All peer-to-peer functionality will be handled identically across platforms, meaning that consumers will not know the difference between connecting to a centralized vendor or using the decentralized capabilities. The framework itself will enable resilient local-first AI experiences, peer-to-peer AI systems that do not require centralized services and the ability to connect to AI vendors - all handled transparently. In the coming months and years, Tether said it will commit substantial resources and investments to the ecosystem to cover functionality and toolkits specifically designed for bleeding-edge use cases such as robotics and brain-computer interfaces.