Frontend Frameworksoya-ann
A lightweight artificial neural network library for JavaScript
- Status
- UnmaintainedNo commits in 690 days.
- Last checked
- Aging · Sep 1, 2026
- License
- Open source
- Pricing
- Free tier · from $0
What it is
Oya-ann is a pure JavaScript artificial neural network library that allows developers to build and train models directly in the browser or on the server. It's ideal for projects requiring deep learning capabilities without external dependencies.
Oya-ann stands out for its simplicity and pure JavaScript approach, making it ideal for educational purposes and lightweight projects without external dependencies.
When it fits — and when it doesn’t
A good fit for
Developers who need a lightweight, pure JavaScript solution for neural networks in browser or server-side projects
Educators and students looking to understand deep learning through hands-on implementation
Look elsewhere if
Projects requiring high-performance GPU acceleration as oya-ann is CPU-based
Large-scale production applications where performance optimization is critical
Known weaknesses
Each one links to the public issue, changelog or docs page it came from, where we have one.
- 01
Limited performance for complex models
Pure JavaScript implementation may not be optimized for heavy computations compared to native libraries or WebAssembly
- 02
Small community and limited third-party support
GitHub repository has low activity with few contributors and limited documentation examples
What it does well
Pure JavaScript implementation for browser and server-side use
Supports various activation functions, loss functions, and optimization algorithms
Lightweight with minimal dependencies
Pricing
- Free tier
- YesOpen source — free to use
- Paid from
- $0
- Model
- Flat rate
- Enterprise plan
- No
Pricing not independently confirmed — check the vendor’s page.
Performance benchmarks
How Fast Is It?
Set up oya-ann
Setup steps, common gotchas and what to check after 30 days.