langchain-init

description	Initialize a new LangChain TypeScript project with recommended config. Use when starting a new LLM-powered app, scaffolding an AI agent project, or setting up LangChain from scratch.
args	[project-name]
allowed-tools	Bash(uv *), Bash(pip *), Bash(python *), Read, Write, Edit
argument-hint	my-agent-project
disable-model-invocation	true
created	"2026-01-08T00:00:00.000Z"
modified	"2026-04-25T00:00:00.000Z"
reviewed	"2026-04-25T00:00:00.000Z"
name	langchain-init

/langchain:init

Initialize a new LangChain TypeScript project with optimal configuration for building AI agents.

When to Use This Skill

Use this skill when...	Use a sibling skill instead when...
Scaffolding a brand-new LangChain TypeScript project from scratch	Adding LangChain to an existing project — use langchain-development
Generating boilerplate, dependencies, and starter config	Building stateful graph workflows — use langgraph-agents
Setting up the canonical project layout the other skills assume	Building hierarchical orchestrators — use deep-agents

Context

Detect the environment:

• node --version - Node.js version
• which bun - Check if Bun is available

Parameters

Parameter	Description	Default
project-name	Name of the project directory	Required

Execution

1. Create Project Directory

mkdir -p $1 && cd $1

2. Initialize Package

If Bun is available:

bun init -y

Otherwise:

npm init -y

3. Install Dependencies

Core packages:

# Package manager: bun or npm
bun add langchain @langchain/core @langchain/langgraph
bun add @langchain/openai  # Default model provider

# Dev dependencies
bun add -d typescript @types/node tsx

4. Create TypeScript Config

Create tsconfig.json:

{
  "compilerOptions": {
    "target": "ES2022",
    "module": "NodeNext",
    "moduleResolution": "NodeNext",
    "esModuleInterop": true,
    "strict": true,
    "skipLibCheck": true,
    "outDir": "dist",
    "declaration": true
  },
  "include": ["src/**/*"],
  "exclude": ["node_modules", "dist"]
}

5. Create Project Structure

mkdir -p src

6. Create Example Agent

Create src/agent.ts:

import { ChatOpenAI } from "@langchain/openai";
import { createReactAgent } from "@langchain/langgraph/prebuilt";
import { tool } from "@langchain/core/tools";
import { z } from "zod";

// Example tool
const greetTool = tool(
  async ({ name }) => `Hello, ${name}!`,
  {
    name: "greet",
    description: "Greet someone by name",
    schema: z.object({
      name: z.string().describe("The name to greet"),
    }),
  }
);

// Create the agent
const model = new ChatOpenAI({
  model: "gpt-4o",
  temperature: 0,
});

export const agent = createReactAgent({
  llm: model,
  tools: [greetTool],
});

// Run if executed directly
if (import.meta.url === `file://${process.argv[1]}`) {
  const result = await agent.invoke({
    messages: [{ role: "user", content: "Say hello to Claude" }],
  });
  console.log(result.messages[result.messages.length - 1].content);
}

7. Create Environment Template

Create .env.example:

# OpenAI (default)
OPENAI_API_KEY=sk-...

# Optional: Anthropic
# ANTHROPIC_API_KEY=sk-ant-...

# Optional: LangSmith tracing
# LANGCHAIN_TRACING_V2=true
# LANGCHAIN_API_KEY=ls__...
# LANGCHAIN_PROJECT=my-project

8. Update package.json Scripts

Add to package.json:

{
  "scripts": {
    "dev": "tsx watch src/agent.ts",
    "start": "tsx src/agent.ts",
    "build": "tsc",
    "typecheck": "tsc --noEmit"
  }
}

9. Create .gitignore

node_modules/
dist/
.env
*.log

Post-Actions

1. Display success message with next steps:

   • Copy .env.example to .env and add API key
   • Run bun dev or npm run dev to start
   • Check LangChain docs for more examples

2. Suggest installing additional model providers if needed:

   • @langchain/anthropic for Claude
   • @langchain/google-genai for Gemini