We Built the First AI-Native Quantum Software Framework: Say Hello to Agentic TensorCircuit-NG

Quantum computing software is notoriously hard to write. If you want to simulate a deep quantum neural network or research a new algorithm, you don't just need to understand Hamiltonian dynamics and Hilbert spaces. You also need to be a High-Performance Computing (HPC) expert—wrestling with GPU memory limits (OOMs), vectorization, JIT compilation staging times, and tensor network contraction paths. For years, we've provided developers with the tools to do this via TensorCircuit-NG , our next-generation open-source, high-performance quantum software framework. But tools are passive. You still have to do the heavy lifting. Today, we are changing the paradigm. We are thrilled to announce that TensorCircuit-NG is now the world’s first AI-native quantum programming platform purpose-built for agentic quantum research and automated scientific discovery. By natively integrating skills directly into our repository, your quantum framework now comes with a built-in HPC engineer, a theoretical phy