Mastra

Pricing

• Framework - free and open source (Apache 2.0)
• Mastra Platform Starter - $0/mo: 100K observability events, 24 CPU hours, 15-day retention, then usage-based
• Mastra Platform Teams - $250/mo: 1M observability events, 250 CPU hours, 6-month retention, multiple teams, SSO and SOC 2 docs
• Enterprise - custom pricing for the platform or licensed self-hosted features (RBAC, SSO, data stays in your VPC)
• Gateway tokens - market rate + 5.5%, or bring your own key

Install

npm create mastra@latest

pnpm create mastra@latest

npm install @mastra/core@latest zod@latest typescript@latest @types/node@latest mastra@latest

Models

Set model as a provider/model string, for example openai/gpt-6.1-sol or anthropic/claude-opus-5-5. Mastra's model router then reads that provider's API key from the environment, and Mastra says the router reaches thousands of models. The create command offers OpenAI, Anthropic, Google and xAI as starting providers.

Recent changes

• Oct 21@mastra/core 1.79.0 adds experimental MCP Events, span aggregation and time-to-first-chunk observability fields, and moves agent controller sessions to session IDs (a breaking change).
• Oct 16@mastra/core 1.78.0 adds agent scopes for multi-tenant identity and memory routing, a trace aggregation API, and typed signal queueing with Agent.queueSignal().
• Oct 14@mastra/core 1.77.0 adds a FactorySandbox provider contract with Docker, E2B, and Mastra Platform sandboxes, plus prebuilt environment builds and multi-repo sessions in Mastra Factory.
• Oct 13@mastra/core 1.76.0 makes durable agent crash recovery safe across instances with run ownership and storage-level run fencing, and adds atomic working-memory merges on PostgreSQL.
• Oct 7@mastra/core 1.75.0 adds a span query API, token and cost measures in trace aggregation, and self-embedding vector stores for semantic recall.

Sources: Mastra pricing, Get started with Mastra, mastra-ai/mastra releases

Similar Tools

AI Frameworks

Vercel AI SDK

The TypeScript toolkit for building AI apps. Unified API across OpenAI, Anthropic, Google. Streaming, tool calling, structured output, multi-step agents. 27K+ GitHub stars.

AI Frameworks

CopilotKit

Frontend stack for agent-native apps. React hooks, prebuilt copilot UI, AG-UI runtime, frontend tools, shared state, and human-in-the-loop flows.

AI Frameworks

LangChain / LangGraph

Most popular LLM framework. 100K+ GitHub stars. Chains, RAG, vector stores, tool use. LangGraph adds stateful multi-agent workflows with cycles and persistence.

AI Frameworks

LlamaIndex

LLM data framework for connecting custom data sources to language models. Best-in-class RAG, data connectors, and query engines. Python and TypeScript.

More AI Frameworks Tools

Vercel AI SDK

The TypeScript toolkit for building AI apps. Unified API across OpenAI, Anthropic, Google. Streaming, tool calling, structured output, multi-step agents. 27K+ GitHub stars.

CopilotKit

Frontend stack for agent-native apps. React hooks, prebuilt copilot UI, AG-UI runtime, frontend tools, shared state, and human-in-the-loop flows.

Claude Agent SDK

Anthropic's SDK for building agents on the same tools, agent loop, and context management that power Claude Code. Python and TypeScript. Subagents, hooks, MCP, and permissions.