JSPM

create-mastra

0.0.0-vnextAgentNetwork-20250527105810
  • ESM via JSPM
  • ES Module Entrypoint
  • Export Map
  • Keywords
  • License
  • Repository URL
  • TypeScript Types
  • README
  • Created
  • Published
  • Downloads 2843
  • Score
    100M100P100Q140252F
  • License Elastic-2.0

Create Mastra apps with one command

Package Exports

  • create-mastra
  • create-mastra/dist/index.js

This package does not declare an exports field, so the exports above have been automatically detected and optimized by JSPM instead. If any package subpath is missing, it is recommended to post an issue to the original package (create-mastra) to support the "exports" field. If that is not possible, create a JSPM override to customize the exports field for this package.

Readme

Create Mastra

The easiest way to get started with Mastra is by using create-mastra. This CLI tool enables you to quickly start building a new Mastra application, with everything set up for you.

Usage

Using npx:

npx create-mastra@latest

Using npm:

npm create mastra@latest

Using yarn:

yarn create mastra

Using pnpm:

pnpm create mastra

Options

  • --default - Quick start with defaults (src directory, OpenAI, no examples)
  • -c, --components <components> - Comma-separated list of components (agents, tools, workflows)
  • -l, --llm <model-provider> - Default model provider (openai, anthropic, groq, google, or cerebras)
  • -e, --example - Include example code

Examples

Create a new project with default settings npx create-mastra@latest --default Create a project with specific components and LLM provider npx create-mastra@latest -c agents,tools -l anthropic Create a project with example code npx create-mastra@latest --example

What's included?

The generated project will have:

  • A configured Mastra setup in the src directory
  • Selected components (agents, tools, workflows)
  • Environment configuration for your chosen LLM provider
  • TypeScript configuration
  • Example code (if selected)

System Requirements

  • Node.js 20 or later
  • MacOS, Windows, and Linux are supported