The Mastra blog

Updates, tutorials, and engineering deep-dives on building AI agents, workflows, and TypeScript tooling with Mastra.

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.

Jul 14, 2026
Sam Bhagwat
# foundations

Introducing Tool Hooks for Mastra Agents

Observe and control every tool call your agent makes.

Jul 14, 2026
Paul Scanlon
# features

Introducing Gates and Verdicts for Mastra Evals

Catch agent regressions and ship with more confidence.

Jul 13, 2026
Paul Scanlon
# features

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.

Jul 10, 2026
Sam Bhagwat
# foundations

Introducing Custom Signal Providers for Mastra Agents

Send notification signals to your agents from any external source.

Jul 9, 2026
Paul Scanlon
# features

Introducing Schedules for Mastra Agents and Workflows

A unified API for managing automated recurring tasks

Jul 8, 2026
Paul Scanlon
# features

Introducing First-Class Skills for Mastra Agents

Attach skills directly to your agents.

Jul 7, 2026
Paul Scanlon
# features

Introducing File-Based Agents for Mastra

Define your agents using folders and files.

Jul 3, 2026
Paul Scanlon
# features

Introducing Browser Recording for Mastra Agents

Record and replay your agent's browser sessions.

Jul 2, 2026
Paul Scanlon
# features

Introducing Webhook Signals for Mastra Agents

Your agents can now react to webhook events from GitHub, Slack, Stripe, or your own API.

Jul 1, 2026
Paul Scanlon
# features

Build Claude Code for X with Agent Controller

Build and control long-running agent experiences with sessions, modes, permissions, subagents.

Jun 30, 2026
Alex Booker
# features

What are durable AI agents? How state persistence and checkpoints survive a restart

A long-running agent is a durable record that short-lived processes take turns with. This walks through why a context window is not a persistence layer, the three granularities of persistence, how Mastra checkpoints a run to JSON and resumes it on a fresh machine, why a worker can't judge its own work, and the two kinds of state a durable agent has to keep.

Jun 30, 2026
Sam Bhagwat
# foundations

Ship better agents