tensorflow/swift

Health v2 · maintenance only

Flags: no_releases archived

Adoption not part of the score

6122 stars · 610 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

Swift for TensorFlow was an experimental next-generation machine learning platform integrating differentiable programming directly into the Swift language. The project was archived in February 2021 and the repository is now read-only, though its ideas live on in the Swift compiler and spin-off projects.

Use cases

• train neural networks in Swift
• differentiable programming with gradients in Swift
• run deep learning models on GPU from Swift
• use Swift in Jupyter notebooks for ML
• learn how ML and compiler design intersect

When to choose

• you want to study archived research on language-integrated differentiable programming
• you need the historical Swift deep learning API or model garden
• you're researching how differentiable programming was added to Swift

When to avoid

• you need a maintained ML framework for production
• you want ecosystem support, updates, or bug fixes
• you're starting a new machine learning project - use PyTorch, JAX, or MLX instead

Facets

library · maturity abandoned

machine-learning deep-learning compiler interpreter machine-learning deep-learning compilers programming-languages differentiable-programming tensorflow archived jupyter-notebooks language-integration swift linux macos gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="tensorflow/swift")