The Mastra blog
Updates, tutorials, and engineering deep-dives on building AI agents, workflows, and TypeScript tooling with Mastra.
Introducing Goals for Mastra Agents
Durable objectives for long-running agents with LLM-judged evaluations.
The 8 Best AI Agent Email Providers (July 2026): Features, Tradeoffs, and Use Cases
This guide compares eight leading AI agent email providers, explains where each one excels, and helps you choose the right email infrastructure for your next AI application.
Introducing Tool Hooks for Mastra Agents
Observe and control every tool call your agent makes.
Introducing Gates and Verdicts for Mastra Evals
Catch agent regressions and ship with more confidence.
What is LLM observability? A span-by-span breakdown
LLM observability records what an agent did at the level of individual model calls and tool executions. This reads the trace of a live agent run span by span from storage, shows what a hallucination and a failed tool call look like, covers where the OpenTelemetry GenAI conventions stand in mid-2026, and walks the four dials that control tracing cost in production.
Introducing Custom Signal Providers for Mastra Agents
Send notification signals to your agents from any external source.
Introducing Schedules for Mastra Agents and Workflows
A unified API for managing automated recurring tasks
Introducing First-Class Skills for Mastra Agents
Attach skills directly to your agents.
Introducing File-Based Agents for Mastra
Define your agents using folders and files.
Introducing Browser Recording for Mastra Agents
Record and replay your agent's browser sessions.
Introducing Webhook Signals for Mastra Agents
Your agents can now react to webhook events from GitHub, Slack, Stripe, or your own API.
Build Claude Code for X with Agent Controller
Build and control long-running agent experiences with sessions, modes, permissions, subagents.
Ship better agents