Memory management for Mastra agents. Visit [the docs](https://mastra.ai/docs/memory/overview) for more information.
LongMemEval benchmark implementation for Mastra Memory
AtomicMemory adapter for Mastra - memory tools around an injected MemoryClient.
Wraps @mastra/memory; pgvector-backed default via @ahamie/storage.
AgentMem integration for Mastra — memory tools for any Mastra agent
Mastra is a framework for building AI-powered applications and agents with a modern TypeScript stack.
Autonomous AI agent with Mastra, memory, planning, and Telegram integration
DynamoDB storage adapter for Mastra
cli for mastra
The official TypeScript library for the Mastra Client API
Implementation of the AG-UI protocol for Mastra.
Local embedding model integration for Mastra, powered by ONNX Runtime.
Typed HTTP handlers and utilities for exposing a `Mastra` instance over HTTP. This package powers `mastra dev` and can be added to your own server to provide REST and streaming endpoints for agents, workflows, telemetry and more.
A coding agent that never compacts. Built with [Mastra](https://mastra.ai) and [pi-tui](https://github.com/badlogic/pi-mono).
Core observability package for Mastra - includes tracing and scoring features
A Vercel deployer for Mastra applications.
Core deployment infrastructure for Mastra applications, handling build, packaging, and deployment processes.
Mastra supports the [Model Context Protocol (MCP)](https://modelcontextprotocol.io/docs/getting-started/intro), an open standard for connecting AI agents to external tools and resources. It serves as a universal plugin system, enabling agents to call tool
Adds custom API routes to be compatible with the AI SDK UI parts
DuckDB vector store provider for Mastra - embedded high-performance vector storage with HNSW indexing
Langfuse observability provider for Mastra - uses official Langfuse v5 SDK
Mastra Express adapter for the server
A collection of logging transport implementations for Mastra, extending the `LoggerTransport` class from `@mastra/core`.
MCP server for accessing Mastra.ai documentation, changelogs, and news.