neuronika/neuronika

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1086 stars · 56 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Neuronika is a machine learning framework written in pure Rust providing tensors and dynamic neural networks with reverse-mode automatic differentiation via a define-by-run API. It focuses on ease of use, fast prototyping, and performance without FFI, with optional CUDA and BLAS feature flags.

Use cases

• build neural networks in pure Rust
• train models with reverse-mode autodifferentiation
• prototype deep learning models without Python
• do tensor math with a define-by-run API
• accelerate training with CUDA
• avoid FFI overhead in ML workloads

When to choose

• you want a pure-Rust deep learning framework with no FFI
• you need dynamic, imperative define-by-run model definitions
• you prefer Rust's safety and performance for ML prototyping

When to avoid

• you need a mature, actively maintained framework with a large ecosystem
• you require production-grade GPU support or extensive model zoo
• you need the latest deep learning features and community support

Facets

library · maturity abandoned

machine-learning deep-learning llm-training machine-learning deep-learning rust cross-platform tensors autodifferentiation neural-networks define-by-run ndarray pure-rust gpu

Member repositories

For agents

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