langchain-ai/langchainjs

LangChain.js is a TypeScript framework for building applications powered by large language models (LLMs, the AI systems behind tools like ChatGPT). It solves the problem of assembling all the pieces needed to make an AI-powered app work together: connecting the AI model to your data sources, chaining together multi-step workflows, and switching between different AI models without rewriting everything when something better comes along. The core idea is modular, component-based architecture. Instead of building everything from scratch, you assemble pre-built pieces: model connectors, data retrievers, vector stores (databases that store content in a format AI can search efficiently), and integrations with external tools. This makes it faster to prototype and also easier to maintain as AI technology changes. LangChain.js can run in many environments including Node.js, Cloudflare Workers, Vercel and Next.js (both server-side and in the browser), Supabase Edge Functions, Deno, and Bun, covering most of the places where modern JavaScript applications run. The ecosystem extends beyond the core library. LangGraph is a companion framework for building agents, AI systems that can plan and take actions over multiple steps. LangSmith is a developer platform for debugging, testing, and monitoring your LLM apps in production. Deep Agents is a higher-level package built on LangChain that adds built-in support for planning, sub-agents, and file system access. You would use LangChain.js if you are building an AI-powered JavaScript or TypeScript application and want a structured, well-supported way to connect AI models to real data and real workflows.