NPM libraries to build your next AI projects

I've gathered my favorite LLM and other related AI libraries I use. The list if for you to build your next big AI project. Yay! 🥳

So, let's dig in! 🔍

EnergeticAI provides an optimized TensorFlow.js version specifically designed for serverless environments. It offers excellent performance and efficiency, making it an ideal choice for deploying machine learning models in serverless settings. If you're looking for a powerful and streamlined solution, EnergeticAI is definitely worth checking out.

Web LLM (AKA WebLLM) is a groundbreaking project that brings the power of large-language models and chat capabilities directly to web browsers. With Web LLM, you can run everything within the browser without the need for server support. This opens up exciting possibilities for creating interactive and intelligent web applications that leverage the capabilities of large-language models.

Wllama is a WebAssembly binding for llama.cpp, enabling in-browser inference of large-language models. It is a very new project, and still quite unknown (only 91 stars on GitHub as of May 10th, 2024), however the library is very promising and two maintainer ship releasing weekly. Wllama provides low-level APIs for tasks such as tokenization, detokenization, and embeddings. With Wllama, you can harness the power of llama.cpp directly within the browser environment, unlocking new possibilities for client-side natural language processing and machine learning applications.

node llama cpp is another one that allows you to run AI models locally with NodeJS.

Rachet ML is a versatile and cross-platform browser ML framework developed by the renowned Hugging Face team. It provides a comprehensive set of tools and libraries for building and deploying machine learning models in web browsers. With Rachet, you can easily create interactive and intelligent web applications that leverage the latest advancements in machine learning technology.

👉 And you? Which one would you use for your next project? 💡