Blog — Jun 2026
Updates, tutorials, and engineering deep-dives on building AI agents, workflows, and TypeScript tooling with Mastra.
Introducing Mastra CLI Actions for Claude Code, Cursor, and Codex
Run, debug, and improve your Mastra agents from the terminal.
What is the Agent2Agent (A2A) protocol? How AI agents delegate work
A2A is a shared standard for one agent to hand work to another on a remote server. This walks through its five-object data model, the agent card, the eight task states, the three ways to watch a task, how trust is decided before work is sent, and how Mastra implements both sides on the official @a2a-js/sdk.
Introducing auto-deployment in Mastra platform
Create and deploy your Mastra platform project from GitHub
Add realtime voice to your Mastra agents with Inworld
Inworld's Realtime API now plugs into Mastra via @mastra/voice-inworld-realtime — one WebSocket session gives your agent speech in/out, semantic turn detection, barge-in, and tool calling, attached to the agent you already have.
Announcing Mastra Harness
Build interactive AI agents with multiple modes, persistent threads, tool approval, and model switching.
Introducing Managed Databases for Mastra Projects
Provision a database for your Mastra project in seconds.
Giving a Mastra agent web access with Bright Data
How a Mastra agent uses Bright Data's webSearch and webFetch in its reasoning loop — what comes back from each tool, why memory turns search into research, and when to choose the typed @mastra/brightdata tools over the Web MCP.
Partnering with Mastra
How technology partners integrate with Mastra — from shipping an integration PR, to co-marketing, to going to market together — with examples from MongoDB, Elastic, Render, CopilotKit, Bright Data, and more.
Introducing Claude Code, Cursor, and Codex agents in Mastra
Build your own coding agents using Claude, Cursor, or OpenAI's agent SDKs.
Product Agents We Built at Mastra
Internal agents help us keep information out of silos, automate work in public, and scale how we listen to users.
Introducing Code Mode for Mastra Agents
Your agents can now run multi-tool computations with more accurate results.
Anatomy of a harness: building a coding agent that can run for hours
How Mastra Code's harness wraps the agent loop: conversation-as-channel, event-to-display-state translation, human-in-the-loop tools, observational memory, subagents, modes, and an ordered tool-approval chain.