LangChain.js Has a Free AI Framework — Build RAG Agents and Chains in TypeScript

Why LangChain.js?

Chains, agents, RAG, memory, 100+ integrations — all type-safe TypeScript.

npm install langchain @langchain/openai @langchain/core

import { ChatOpenAI } from "@langchain/openai"
const model = new ChatOpenAI({ model: "gpt-4o" })
const response = await model.invoke([{ role: "user", content: "What is web scraping?" }])

RAG in 5 Lines

import { MemoryVectorStore } from "langchain/vectorstores/memory"
import { OpenAIEmbeddings } from "@langchain/openai"
import { RecursiveCharacterTextSplitter } from "langchain/text_splitter"

const docs = await new RecursiveCharacterTextSplitter({ chunkSize: 1000 }).createDocuments([text])
const store = await MemoryVectorStore.fromDocuments(docs, new OpenAIEmbeddings())
const results = await store.asRetriever().invoke("key points?")

Agents

import { createReactAgent } from "@langchain/langgraph/prebuilt"
const agent = createReactAgent({ llm: new ChatOpenAI(), tools: [searchTool] })

Feature	LangChain.js	Vercel AI SDK
RAG	Built-in	Manual
Agents	LangGraph	Basic
Best for	Complex AI	Chat UIs

---

Need to extract data from any website at scale? I build custom web scrapers — 77 production scrapers running on Apify Store. Email me at [e-mail] for a tailored solution.