Private

马斯特拉

Try Now

21 分钟前

打字稿AI代理框架。 ⚡助手，抹布，可观察性。支持任何LLM：GPT-4，Claude，Gemini，Llama。

3 years

Works with Finder

49

Github Watches

618

Github Forks

12k

Github Stars

Mastra

Mastra is an opinionated TypeScript framework that helps you build AI applications and features quickly. It gives you the set of primitives you need: workflows, agents, RAG, integrations and evals. You can run Mastra on your local machine, or deploy to a serverless cloud.

The main Mastra features are:

Features	Description
LLM Models	Mastra uses the Vercel AI SDK for model routing, providing a unified interface to interact with any LLM provider including OpenAI, Anthropic, and Google Gemini. You can choose the specific model and provider, and decide whether to stream the response.
Agents	Agents are systems where the language model chooses a sequence of actions. In Mastra, agents provide LLM models with tools, workflows, and synced data. Agents can call your own functions or APIs of third-party integrations and access knowledge bases you build.
Tools	Tools are typed functions that can be executed by agents or workflows, with built-in integration access and parameter validation. Each tool has a schema that defines its inputs, an executor function that implements its logic, and access to configured integrations.
Workflows	Workflows are durable graph-based state machines. They have loops, branching, wait for human input, embed other workflows, do error handling, retries, parsing and so on. They can be built in code or with a visual editor. Each step in a workflow has built-in OpenTelemetry tracing.
RAG	Retrieval-augemented generation (RAG) lets you construct a knowledge base for agents. RAG is an ETL pipeline with specific querying techniques, including chunking, embedding, and vector search.
Integrations	In Mastra, integrations are auto-generated, type-safe API clients for third-party services that can be used as tools for agents or steps in workflows.
Evals	Evals are automated tests that evaluate LLM outputs using model-graded, rule-based, and statistical methods. Each eval returns a normalized score between 0-1 that can be logged and compared. Evals can be customized with your own prompts and scoring functions.

Quick Start

Prerequisites

Node.js (v20.0+)

Get an LLM provider API key

If you don't have an API key for an LLM provider, you can get one from the following services:

If you don't have an account with these providers, you can sign up and get an API key. Anthropic require a credit card to get an API key. Some OpenAI models and Gemini do not and have a generous free tier for its API.

Create a new project

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.

npx create-mastra@latest

Run the script

Finally, run mastra dev to open the Mastra playground.

npm run dev

If you're using Anthropic, set the ANTHROPIC_API_KEY. If you're using Gemini, set the GOOGLE_GENERATIVE_AI_API_KEY.

Contributing

Looking to contribute? All types of help are appreciated, from coding to testing and feature specification.

If you are a developer and would like to contribute with code, please open an issue to discuss before opening a Pull Request.

Information about the project setup can be found in the development documentation

Support

We have an open community Discord. Come and say hello and let us know if you have any questions or need any help getting things running.

It's also super helpful if you leave the project a star here at the top of the page

Reviews

2 (1)

user_XvtCMZFo

2025-04-18

I have been using Mastra for a while now, and it has transformed how I approach machine learning projects. It is well-documented and user-friendly, making complex processes much more manageable. The GitHub repository is regularly updated, ensuring I have access to the latest features and improvements. Highly recommended for both beginners and advanced users! Check it out via their GitHub page.