We added sleep methods to workflows, structured memory to agents, and a new Gladia STT provider.
How PLAID Japan migrated from GUI-based AI tools to Mastra for better collaboration and productivity for their engineering team building on Google Cloud.
Cross-thread memory recall, universal schema support, and enhanced workflow observability.
How Vetnio uses Mastra's workflow orchestrator to build specialized veterinary AI assistants
Why Fireworks AI decided to ship AIML, a prompt-based agent framework, using Mastra.
Mastra 101, Mastra Auth, and more
A deep dive into building MastraManus, an AI research assistant powered by Mastra's vNext workflows.
The newest (and perhaps coolest) way to learn Mastra
We're excited to announce the release of v2 of Principles of Building AI Agents.
How Lua switched from custom agent infrastructure to Mastra Cloud for rapid deployment of 100+ business partners across African markets.
How MedusaJS used Mastra Cloud to prototype and deploy agent architectures for automated e-commerce feature generation.
MCP Server updates, streaming support, and more.
