Skills DirectorySearch all skills ↗

AI agent skill · by @olorehq

Olore Mastra Latest

Local Mastra documentation reference (latest). Mastra documentation. Use for TypeScript AI agents, tools, RAG, workflows, MCP integration, voice, and AI application framework.

Archived 2026-10-23 · Source updated 2026-09-18 · License: MIT. Check the original repository for the latest version.

SKILL.md instructions

# Mastra Documentation

Mastra is a TypeScript framework for building AI agents, multi-step workflows, and AI-powered applications. It provides agents with tools, memory, RAG, voice, MCP integration, streaming, and production deployment infrastructure.

## Quick Reference

| Task | Entry Point |
|------|-------------|
| Getting started | `contents/index.mdx` |
| Build an agent | `contents/agents/overview.mdx` |
| Create a workflow | `contents/workflows/overview.mdx` |
| Add memory to agents | `contents/memory/overview.mdx` |
| Set up RAG | `contents/rag/overview.mdx` |
| MCP integration | `contents/mcp/overview.mdx` |
| Server configuration | `contents/server/mastra-server.mdx` |
| Deploy to production | `contents/deployment/overview.mdx` |
| Observability / tracing | `contents/observability/overview.mdx` |
| Evaluate agents | `contents/evals/overview.mdx` |

## When to use

Use this skill when the user asks about:
- Building TypeScript AI agents and agent networks
- Mastra workflows, control flow, suspend/resume, and human-in-the-loop
- Agent memory (working memory, semantic recall, message history, observational memory)
- Retrieval-Augmented Generation (RAG), chunking, embedding, vector databases
- Model Context Protocol (MCP) integration and MCP apps
- Streaming agent and workflow output
- Voice features (TTS, STT, speech-to-speech)
- Agent evaluations and custom scorers
- Mastra server setup, auth, custom routes, middleware
- Deployment to cloud providers, monorepos, web frameworks
- Observability, tracing, logging, metrics, and exporter integrations
- Browser automation with AgentBrowser, Stagehand, or BrowserViewer
- Workspace, filesystem, sandbox, and code intelligence for agents
- Studio UI for development and team collaboration
- Mastra Platform for hosted observability, Studio, and Server

## How to find information

1. **First**, read `TOC.md` for the complete file listing organized by directory
2. Identify the relevant section based on the user's question
3. Read specific files for implementation details

**TOC.md contains all 147 files organized by directory - always check it first.**

Related skills