# JavaScriptAI

> A curated directory of 23 AI tools, libraries and frameworks for JavaScript and TypeScript developers, in 5 categories.

Use it to choose a JavaScript or TypeScript library for an AI job: calling a model, building an agent or RAG app, running a model in the browser, storing embeddings, or coding with AI. Each category page explains what the category is, how to choose, and common questions.

- The same list as JSON: https://javascriptai.com/tools.json
- Updated: 2026-11-03

## Categories

- [JavaScript AI Frameworks](https://javascriptai.com/frameworks): Full-featured JavaScript frameworks for building AI-powered applications with LLMs, agents, and retrieval pipelines.
- [JavaScript LLM SDKs](https://javascriptai.com/llm-sdks): Official JavaScript and TypeScript SDKs for connecting to large language model APIs from OpenAI, Anthropic, Google, and more.
- [Machine Learning in the Browser with JavaScript](https://javascriptai.com/browser-ml): Run machine learning models directly in the browser or Node.js — no Python server required.
- [AI Developer Tools for JavaScript](https://javascriptai.com/ai-dev-tools): AI-powered developer tools that help JavaScript developers write, review, and ship code faster.
- [Vector Databases for JavaScript](https://javascriptai.com/vector-databases): JavaScript clients for vector databases — store and search embeddings for RAG, semantic search, and AI memory.

## Frameworks

- [Vercel AI SDK](https://ai-sdk.dev/): The TypeScript toolkit for building AI apps. Streaming UI, tool calling, and multi-provider support. GitHub: https://github.com/vercel/ai
- [LangChain.js](https://js.langchain.com/): Framework for building LLM-powered apps. Chains, agents, retrieval, and memory out of the box. GitHub: https://github.com/langchain-ai/langchainjs
- [LlamaIndex.TS](https://ts.llamaindex.ai/): Data framework for LLM apps in TypeScript. Connect your data to large language models. GitHub: https://github.com/run-llama/LlamaIndexTS
- [Mastra](https://mastra.ai): Open-source TypeScript framework for AI agents and workflows. Memory, observability, and integrations with React, Next.js, and Node. GitHub: https://github.com/mastra-ai/mastra
- [ModelFusion](https://github.com/vercel/modelfusion): Archived TypeScript library for multimodal AI apps. Retained as a historical reference; use AI SDK for new projects. GitHub: https://github.com/vercel/modelfusion

## LLM SDKs

- [Anthropic SDK](https://docs.anthropic.com/en/api/client-sdks): Official TypeScript SDK for Claude. Build conversational AI, code generation, and analysis tools. GitHub: https://github.com/anthropics/anthropic-sdk-typescript
- [OpenAI Node](https://platform.openai.com/docs): Official Node.js library for the OpenAI API. GPT, DALL-E, Whisper, and embeddings. GitHub: https://github.com/openai/openai-node
- [Google Gen AI SDK](https://ai.google.dev/gemini-api/docs/libraries): Official JavaScript and TypeScript SDK for Gemini. Use the maintained @google/genai package. GitHub: https://github.com/googleapis/js-genai
- [Mistral JS Client](https://docs.mistral.ai/): TypeScript client for Mistral AI models. Fast, efficient open-weight model access. GitHub: https://github.com/mistralai/client-js
- [Cohere Node SDK](https://docs.cohere.com/): Official TypeScript SDK for Cohere. Embeddings, reranking, and RAG-optimized models. GitHub: https://github.com/cohere-ai/cohere-typescript

## ML & Browser AI

- [TensorFlow.js](https://www.tensorflow.org/js): Machine learning for JavaScript. Train and deploy ML models in the browser and Node.js. GitHub: https://github.com/tensorflow/tfjs
- [ONNX Runtime Web](https://onnxruntime.ai/): Run ONNX models in the browser with WebAssembly and WebGPU acceleration. GitHub: https://github.com/microsoft/onnxruntime
- [Transformers.js](https://huggingface.co/docs/transformers.js): Run Hugging Face transformers directly in the browser. NLP, vision, and audio — no server needed. GitHub: https://github.com/huggingface/transformers.js
- [WebLLM](https://webllm.mlc.ai/): Run large language models entirely in the browser using WebGPU. Private, fast, offline-capable. GitHub: https://github.com/mlc-ai/web-llm
- [Brain.js](https://brain.js.org/): GPU-accelerated neural networks in JavaScript. Simple API for training and running neural nets. GitHub: https://github.com/BrainJS/brain.js

## AI Dev Tools

- [Claude Code](https://docs.anthropic.com/en/docs/claude-code): Anthropic's agentic coding tool. An AI assistant that lives in your terminal and understands your codebase.
- [Cursor](https://cursor.sh/): AI-first code editor built on VS Code. Inline AI editing, chat, and codebase-aware completions.
- [GitHub Copilot](https://github.com/features/copilot): AI pair programmer by GitHub. Code suggestions, chat, and pull request summaries.
- [v0 by Vercel](https://v0.dev/): AI-powered UI generation. Describe a component and get production-ready React code.

## Vector & Data

- [Pinecone JS Client](https://www.pinecone.io/): TypeScript client for Pinecone vector database. Serverless vector search at scale. GitHub: https://github.com/pinecone-io/pinecone-ts-client
- [ChromaDB JS](https://www.trychroma.com/): JavaScript client for Chroma, the open-source embedding database for AI apps. GitHub: https://github.com/chroma-core/chroma
- [Weaviate JS Client](https://weaviate.io/): TypeScript client for Weaviate vector database. Semantic search and hybrid retrieval. GitHub: https://github.com/weaviate/typescript-client
- [Turbopuffer JS](https://turbopuffer.com/): TypeScript client for Turbopuffer. Fast, cost-effective serverless vector database.

## About

Listings are editorial: no tool pays to be listed. Suggest a tool: https://javascriptai.com/#submit-a-tool