About
What is mastra?
Mastra is a comprehensive framework designed for building AI-powered applications and agents with a modern TypeScript stack. Developed by the team behind Gatsby, it offers everything needed to go from early prototypes to production-ready applications. Key features include model routing, which connects to over 40 providers like OpenAI, Anthropic, and Gemini through a single interface. It enables the creation of autonomous agents that use LLMs and tools to solve open-ended tasks, and a graph-based workflow engine for orchestrating complex multi-step processes. Mastra also supports human-in-the-loop interactions, context management for agents, and integrations with existing React, Next.js, or Node.js apps. It emphasizes production essentials with built-in evals and observability for continuous refinement of AI products.
Best used for
Ideal for developers who need to build AI-powered applications and agents, orchestrate complex multi-step AI processes, and integrate AI capabilities into existing web or Node.js apps. Especially valuable for those seeking a robust, TypeScript-first framework with built-in tools for reliability and scalability.
Common actions
open-sourceautomated workflowdeepfakelow-code/no-codecollaboration"AI Agents"github copilotface swappingworkflows
Capabilities
Key features
- Model routing (40+ providers)
- Autonomous AI agents
- Graph-based workflow engine
- Human-in-the-loop support
- Context management for agents
- Built-in evals and observability
- TypeScript stack
Integrations
Not yet documentedPricing & Plans
Open Source ยท Enterprise
FAQs
What is the primary programming language used with Mastra?
Mastra is built with a modern TypeScript stack, making it ideal for developers who prefer working with TypeScript for building AI-powered applications and agents. It leverages TypeScript's features for robust and scalable development.
Does Mastra support multiple AI model providers?
Yes, Mastra features model routing that allows connection to over 40 different AI model providers, including OpenAI, Anthropic, and Gemini, through a single standardized interface. This provides flexibility in choosing and switching models.
How does Mastra handle complex AI workflows?
Mastra includes a graph-based workflow engine that enables developers to orchestrate complex multi-step processes with explicit control over execution. It uses an intuitive syntax for control flow, such as .then(), .branch(), and .parallel().
Is Mastra suitable for production-ready AI applications?
Yes, Mastra is designed for production-ready applications, offering built-in evals and observability tools. These features help developers continuously observe, measure, and refine their AI products for reliability and performance in real-world scenarios.
What is the licensing model for Mastra?
Mastra uses a dual-license model. The core framework is open source under Apache License 2.0. However, code in directories named 'ee/' is source-available under the Mastra Enterprise License, requiring a valid enterprise license for production use.