LangChain + Next.js Template

Dependency freshness

Declared = lowest version the kit's dependency file (package.json, pyproject.toml or requirements.txt) allows. Latest = the npm "latest" tag or the newest PyPI release. TypeScript, the Stripe SDK, FastAPI and other 0.x packages are shown but not counted in the verdict.

What's in the stack

Framework

Next.js

Database / ORM

Supabase

UI

Tailwind CSS, Radix UI

AI

Vercel AI SDK, LangChain

Detected from declared dependencies. A listed package means it's installed, not necessarily fully wired up.

What the README says you get

• AI
  Simple chatSimple chat
• AI
  Structured LLM outputReturning structured output from an LLM call
• AI
  Multi-step agentsAnswering complex, multi-step questions with agents
• AI
  RAG with chainRetrieval augmented generation (RAG) with a chain and a vector store
• AI
  RAG with agentRetrieval augmented generation (RAG) with an agent and a vector store
• AI
  Token streaminguse Vercel's AI SDK to stream tokens to the client
• AI
  LangGraph agent workflowsThe agents use LangGraph.js, LangChain's framework for building agentic workflows
• AI
  Zod schema outputuses a popular library called Zod to construct a schema
• AI
  Web search agentset `TAVILY_API_KEY` in `.env.local` for web search
• AI
  Calculator toolThe calculator accepts two numbers and an arithmetic operation
• AI
  Cited sourcesreturn cited sources via header in addition to the streaming response
• Data
  Supabase vector storeuse Supabase as a vector store through a small local adapter
• Deploy
  Vercel deploymentyou can deploy your app on the Vercel Platform
• Testing
  Integration testsRun the calculator and mock-backed Supabase regression tests

Extracted from the kit's README by a local AI model (deepseek-flash) on Sep 29, 2026. Every item is checked against an exact README quote. A README claim is the maker's description, not something we tested.