The Mastra blog

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

All Posts Announcements Features Examples Foundations

Announcing Mastra Factory Beta

How we learned to stop worrying and let the agents ship

# announcements

Introducing Filesystem Mounts for Mastra Workspaces

Read and write to multiple filesystems using the same file interface.

Remote Filesystem Support for Mastra Agents

Give your agents access to filesystems your team already use.

Introducing Sandbox Lifecycle Controls in Mastra

Control, status, hooks, persistence, and background processes.

Introducing Sandbox Computer Use for Mastra Agents

Give your agents a computer to use, just like you do.

Introducing Harness Channels

Run a multi-player harness from Slack, iMessage, WhatsApp, Discord, and more.

Introducing Token Limiting for Mastra Agents

Real-time caps on context window and response lengths.

Introducing Token Cost Control for Mastra Agents

Real-time spending caps configurable by thread, user, session, org, and more.

Introducing the Mastra Helm Chart for Self-Hosted Deployments

Kubernetes best practices for your self-hosted Mastra project.

Introducing Skill Search for Mastra Agents

Load agent skills on demand to reduce context bloat, token usage and cost.

Introducing Tool Search for Mastra Agents

Load agent tools on demand for sharper tool selection, lower token usage, and less cost.

Introducing Multi-turn Evals for Mastra Agents

Assert multi-turn conversations using deterministic gates and LLM-as-judge scorers.

Ship better agents

Create a new Mastra project. Mastra is a framework for AI applications and agents on a modern TypeScript stack. Before running the command, ask these questions one at a time and wait for each answer unless it was already provided:

Project name? (default: "my-mastra-app")
Provider? (required; options: "openai", "anthropic", "google", "xai")
If the provider isn't supported, ask again and list the supported values.

Run: `npm create mastra@latest <project-name> -- --llm <provider>`

The command creates a default Mastra project, installs Mastra skills for detected coding assistants, and initializes Git when appropriate.

After creation, enter the project directory and start the dev server: `npx bgproc start -n <project-name> -w -- npm run dev`

Open Mastra Studio at `http://localhost:4111`. Studio is the interface for building, testing, and managing agents, workflows, and tools.

Also mention that the Mastra model router provides access to thousands of models: https://mastra.ai/models