We’re excited to announce LangGraph Templates—available now in Python and JavaScript! These templates address common agentic use cases, allowing you to easily configure and deploy them to LangGraph Cloud. Whether you're a beginner or an experienced developer, LangGraph Templates provide a clear starting point for building sophisticated, customizable applications.

Why LangGraph Templates?

• Full Customizability: Templates give you access to all the agent code. Clone the repo and modify prompts, chaining logic, or any part of the code to suit your needs.

• Easy Debugging & Deployment: Load templates in LangGraph Studio for debugging or deploy them with a single click to LangGraph Cloud.

• Configurable Fields: Use different language models, vector stores, and tools by configuring fields directly in the template setup, making provider choice flexible and customizable.

What’s Included?

For this launch, we’re focusing on a small number of high-quality templates:

1. RAG Chatbot
   A chatbot that retrieves data from a source like Elastic and generates responses based on that data.

2. ReAct Agent
   A versatile agent architecture that uses tools dynamically to handle tasks, looping until completion.

3. Data Enrichment Agent
   Designed for research tasks, this agent fills out forms by conducting searches and verifying its responses. Watch a YouTube walkthrough of this template.

4. Blank Template
   Want to start from scratch? The blank template lets you build your own LangGraph application from the ground up.

What’s Next?

We’re starting with a small number of providers, and more templates are on the way. Our goal is to make these templates high-quality and provider-agnostic, so you can adapt them as needed.

Get started by checking out our Templates Homepage and explore what LangGraph can do for your agentic applications! Read more about how to use templates in our blog post: https://blog.langchain.dev/launching-langgraph-templates/