Open-source TypeScript framework for building, running, and observing AI agents in production.
Mastra is a TypeScript framework that gives developers building blocks for AI agents: workflow orchestration, memory management, tool calling, and observability for agents meant to run for extended periods rather than a single request-response turn. The core framework is open source under the Apache 2.0 license and has accumulated tens of thousands of GitHub stars, with paid enterprise features available under a separate license for teams that need them. Mastra is built by the team behind the Gatsby JavaScript framework and is backed by Y Combinator and Spark Capital, having raised a seed and Series A round. It supports over 90 model providers, integrates with frameworks like Next.js and Node.js, and deploys to targets including Vercel, Netlify, and Cloudflare.
Open-source core is free to use with no seat or usage tiers; a separate paid Enterprise License exists for additional features but its price is not published.
Use tool ↗Mastra brings the same team that scaled Gatsby to millions in revenue into the agent-framework space, and the open-source core with a large provider list is a credible starting point for TypeScript teams. It competes directly with more established orchestration frameworks, so the deciding factor is usually which one already fits a team's existing stack.
Watch out: Enterprise features sit under a separate license from the open-source core, so confirm which features you need are actually included before assuming the free version covers a production deployment.
Side-by-side fact sheets against the competitors our research names — pricing, platforms, API and both verdicts on one page.
No reviews yet — be the first to review Mastra.
Reviews are tied to your EffectHub account — one review per tool, so the rating for Mastra reflects real users.
No questions yet — ask the first one about Mastra.
Questions about Mastra are tied to your EffectHub account, so answers can reach you and the section stays free of spam.