Langchain Typescript Quickstart

From the author

Scaffold a minimal local LangChain agent in TypeScript by following the official quickstart. Use when the user wants to quickly build or try a LangChain agent locally.

— the description by LangChain

AutoGineer summary

Written by AutoGineer from the skill’s own files, not by the author

This skill provides a structured workflow for developers to initialize a local LangChain agent using TypeScript. It ensures adherence to the official documentation while maintaining a clean project structure. The process includes selecting a preferred LLM provider, setting up a dedicated directory, managing environment variables securely, and executing a functional weather agent example.

What it does

Initializes a new project directory for LangChain development.
Prompts the user to select a specific LLM provider and model.
Configures the project to use the selected model while remaining model-agnostic.
Sets up a secure .env file for API key management.
Installs necessary provider-specific packages.
Executes a sample weather agent to verify the local setup.

When to use it

When you need to quickly prototype a LangChain agent locally.
When you want to experiment with different LLM providers using a consistent codebase.
When you are starting a new project and want to follow official LangChain best practices.

Advantages

Ensures project isolation by creating a dedicated directory.
Promotes security by keeping API keys in gitignored environment files.
Provides flexibility by allowing users to switch between various LLM providers.
Reduces setup friction by automating the scaffolding process.

Usage examples

“Help me set up a new LangChain agent in TypeScript.”: The agent will create a new directory, ask for your preferred model, configure the environment, and run a basic weather agent example.

Install

Download the skill as a ZIP:
https://mp-staging.autogineer.com/agent-skills/langchain-ai/langchain-typescript-quickstart/download

Unzip it into the cross-client skills folder of your project:

mkdir -p .agents/skills && unzip langchain-typescript-quickstart.zip -d .agents/skills

Documentation by LangChain

Follow the live docs — do not invent an alternate API from memory:

https://docs.langchain.com/oss/javascript/langchain/quickstart

Fetch that page (Docs MCP or HTTP) and implement what it shows (weather agent + createAgent). Requires Node 22+.

Local setup constraints

Apply these on top of the quickstart (they keep setup minimal and model-agnostic):

Ask which provider/model to use. Showcase that LangChain is model-agnostic. Suggested prompt:
Which model should this agent use? Pass a provider:model string — e.g. openai:gpt-5.5, anthropic:claude-sonnet-5, google-genai:gemini-2.5-flash-lite. Default if you're unsure: anthropic:claude-sonnet-5.
Swap the quickstart's model string for their choice (or the default).
Create a new directory (e.g. langchain-agent/) and do all work there — do not pollute the open project.
Only secret: the provider API key in .env (gitignored). No LangSmith / Tavily unless they ask. Prefer they edit .env themselves — don't paste keys into chat.
Install the provider package needed for their model if the quickstart's base install isn't enough.
Run the example, show output, then stop. Point to langchain-fundamentals for next steps.

Files

ATTRIBUTION.mdAdded by AutoGineer924 B
LICENSELicence file added by AutoGineer1.0 KiB
SKILL.md1.5 KiB

SKILL.md