#182 · Primary category： Inference & Local Deploy
keras-js
Run Keras models in the browser, with GPU support using WebGL
Project last updated：06/15/22
GitHub Stars
5.0K
Forks
491
Contributors
13
License
MIT
Why we included this project
Keras.js lets you take a Keras model and run it entirely inside a browser, using WebGL 2 to offload computation to the GPU while still offering a CPU-only path in Node.js. Because Keras abstracts its backends, you can train with TensorFlow or CNTK and then serve the finished network fully client-side, with no Python server behind it. The repository includes a practical set of demos, from MNIST convnets and ImageNet classifiers like ResNet-50 and Inception v3 to a bidirectional LSTM for sentiment analysis, which makes it a useful reference for structuring browser-based inference projects. Teams building client-side demos or web tools that need to keep computation in the browser will find the architecture instructive. Note that the project is archived and no longer maintained, so it is a learning resource rather than a dependency for new products.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
ollama
Get up and running with Kimi-K2.6, GLM-5.2, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
llama.cpp
LLM inference in C/C++
vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
gpt4all
GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.
LocalAI
LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.