skills.rest
langchain-ai
langchain-aiOFFICIAL
Explore all skills by this author →
Website𝕏@LangChainGitHub

langgraph-typescript-quickstart

Scaffolds a minimal local LangGraph agent in TypeScript following the official quickstart.

1.2k|90|Updated Jan 22, 2026
Search Tags:#langgraph#Langchain#Quickstart#typeScript#Agent#Scaffold#chat model
One-click install
npx skills add https://github.com/langchain-ai/langchain-skills --skill langgraph-typescript-quickstart
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: langgraph-typescript-quickstart
Source: https://github.com/langchain-ai/langchain-skills/tree/main/config/skills/langgraph-typescript-quickstart
Command: npx skills add https://github.com/langchain-ai/langchain-skills --skill langgraph-typescript-quickstart

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Setting up a first LangGraph agent in TypeScript involves navigating documentation, choosing a model provider, and configuring a project correctly, which can be error-prone when done from memory.

Core Features & Use Cases

  • Docs-Grounded Scaffolding: Fetches the official LangGraph JavaScript quickstart and implements the calculator/math agent exactly as documented, preferring the Graph API over the Functional API.
  • Model-Agnostic Setup: Prompts for a provider:model string (e.g. anthropic:claude-sonnet-5, openai:gpt-5.5) and wires it via initChatModel, with provider-specific constraints like omitting temperature on Claude Sonnet 5+.
  • Isolated Project Setup: Creates a new directory, installs only the required packages, and keeps secrets in a gitignored .env file.
  • Use Case: A developer wants to try LangGraph locally for the first time; the agent scaffolds a working math agent in a fresh directory, runs an example query like "Add 3 and 4.", and shows the output.

Quick Start

Ask your coding agent to scaffold a minimal local LangGraph agent in TypeScript using the official quickstart with your preferred model provider.

Frequently Asked Questions about langgraph-typescript-quickstart

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I build a LangGraph agent in TypeScript?▼

Follow the official LangGraph JavaScript quickstart, which builds a calculator/math agent using the Graph API. Create a new directory, install the quickstart packages plus your model provider package, and run the example to verify it works.

Which models can I use with LangGraph in TypeScript?▼

LangGraph works with any LangChain chat model via initChatModel using a provider:model string, such as anthropic:claude-sonnet-5, openai:gpt-5.5, or google-genai:gemini-2.5-flash-lite. For Claude Sonnet 5+, omit temperature, top_p, and top_k parameters.

Should I use the Graph API or Functional API in LangGraph?▼

The quickstart prefers the Graph API path over the Functional API unless you specifically request otherwise. The Graph API is the standard approach shown in the official LangGraph documentation for building agents.

Do I need LangSmith or Tavily API keys for the LangGraph quickstart?▼

No, the only secret required is your model provider API key stored in a gitignored .env file. LangSmith and Tavily are optional and should only be added if you explicitly request them.

What is the difference between LangGraph and LangChain createAgent?▼

LangGraph's Graph API gives explicit control over agent state and flow, while LangChain's createAgent offers a higher-level agent API. For a simpler abstraction after the quickstart, use createAgent instead.

Related Skills

Explore More Software Engineering Skills→
vanman2024vanman2024
10

provider-config-validator

Validate Vercel AI SDK provider configurations and generate fixes.

Community
Intermediate
jxtngxjxtngx
2

langchain-middleware

Implement human-in-the-loop approval and custom middleware for LangChain agents.

Community
Advanced
artgaurav16420-ossartgaurav16420-oss

langsmith-fetch

Fetch and analyze recent LangSmith traces to debug LangChain and LangGraph agents.

Community
Intermediate
langchain-ailangchain-ai
113

langchain-agents

Automate construction of LangChain agents using LangGraph patterns and context management.

Official
Advanced