langchain-init

description	Initialize a new LangChain TypeScript project. Use when starting an 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": {