Mastra
Verified Oct 15, 2026 ActiveOpen-source TypeScript framework for building, running, and observing AI agents in production.
Listed on EffectHub ·
Pricing
- Pricing model
- Freemium
- Paid options from
- $250/mo
- Billing
- Monthly
The Apache 2.0 framework is free to self-host; the hosted Mastra Platform has a free Starter tier (100K observability events, 24 CPU hours, 15-day retention) and a Teams plan at $250/month with metered overage for events, CPU time, storage and gateway tokens at market rate plus 5.5%. Enterprise, cloud or self-hosted, is quote-only.
Use tool ↗About Mastra
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.
- Platforms
- Web · API
- API
- Yes
- Last verified
- Oct 15, 2026
Verified sources
- Pricing page lists a free Starter cloud tier, Teams at $250 per month with 1M observability events and 250 CPU hours, custom Enterprise, and a free Apache 2.0 self-hosted option (15 October 2026)mastra.ai ↗
- Terms of Service name Kepler Software Inc., a Delaware corporation doing business as Mastra, with a San Francisco address (15 October 2026)mastra.ai ↗
- About page says the team previously built Gatsby and is based in San Francisco (15 October 2026)mastra.ai ↗
- Company raised a $13M seed from Y Combinator and others, then a $22M Series A led by Spark Capitalmastra.ai ↗
Is Mastra legit?
We don’t label tools safe or unsafe. Below are the records we checked ourselves, each with the date we read it.
- Domain registered
- Oct 1, 2024 (2 years ago)Registry record (RDAP), registrar Name.com, Inc., looked up Sep 20, 2026
- TLS certificate
- Issued by Let's Encrypt, valid until Nov 21, 2026Seen in our own connection to the site on Oct 15, 2026
- Last checked
- Oct 15, 2026The site answered
- On the market since
- 2024The vendor's own material, read by us
- Operated by
- Kepler Software Inc., United StatesOur research, card verified Oct 15, 2026
Pros & cons of Mastra
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.
Pros
- Apache 2.0 open-source core with a large, active GitHub following
- Built-in workflow, memory, and observability primitives rather than requiring separate tools
- Backed by experienced founders and well funded, reducing near-term abandonment risk
Cons
- TypeScript-only, so it does not serve Python-first agent teams
- Enterprise licensing terms and pricing are not published publicly
- Being newer than incumbents like LangChain means a smaller base of production war stories
Best for
- TypeScript and JavaScript teams building agents who want to stay in one language end-to-end
- Developers who want built-in memory and observability rather than assembling them separately
Not for
- Python-first teams, who are better served by frameworks built natively for that ecosystem
- Teams wanting a no-code agent builder rather than a code framework
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.
Alternatives to Mastra
Mastra head-to-head
Side-by-side fact sheets against the competitors our research or their makers name — pricing, platforms, API and both verdicts on one page.