Download
VibeTensor is a groundbreaking open-source research system software stack for deep learning that was uniquely generated almost entirely by AI coding agents under guided human supervision, demonstrating a new frontier in AI-assisted software engineering. It implements a PyTorch-style eager tensor library with a modern C++20 core that supports both CPU and CUDA backends, giving it the ability to manage tensors, automatic differentiation (autograd), and complex computation flows similar to mainstream frameworks. What makes VibeTensor remarkable is that every major component, from core libraries and dispatch systems to CUDA runtime support, caching allocators, and language bindings, was created and validated by coding agents using automated builds and tests rather than manual line-by-line human coding. The system includes both a Python frontend via a torch-like API and an experimental Node.js/TypeScript interface.
Features
- Deep learning tensor runtime fully generated by AI coding agents
- PyTorch-style eager execution with autograd support
- C++20 core with custom CUDA runtime and caching allocator
- Python API and experimental Node.js/TypeScript bindings
- Dynamic plugin support via stable C ABI
- Built-in multi-GPU experimental execution paths
Project Samples
