Home / Directory / Agents & orchestration / Agent platforms & frameworks / Mastra
Mastra
Open-source TypeScript framework for agents and workflows, with memory, tools, evals, tracing, and a Studio/server platform for running agents in production. Mastra raised a $22 million Series A in April 2026, bringing total funding to $35 million.
TypeScript teams that want agents inside normal web apps with typed workflows, memory, evals, and a studio, without switching the stack to Python notebooks.
Python-first research labs standardized on LangChain/LlamaIndex ecosystems, or buyers who only need a single chatbot widget.
Verdict
Mastra is an open-source TypeScript agent framework from the team behind Gatsby, now paired with Studio, Server, and Memory Gateway platform pieces. Releases include Mastra 1.0 and Factory. It is in production use at Replit, Brex, MongoDB, Workday, and Salesforce.
Score Breakdown
How Mastra scores in the categories that matter to its buyers.
Pricing
The framework is open source. The Mastra platform has a free Starter plan, a Teams plan at $250 a month, and custom Enterprise pricing, with usage metered.
The Field at a Glance
Where Mastra ranks among Agent platforms & frameworks vendors we reviewed, by Overall Score and relative typical engagement cost.
Mastra scores 7.6, just above Kore.ai (7.5) and below LangChain (8.0). Relative cost stays lower while teams run the open-source framework and rises with hosted platform usage.
Use-case matrix
| Use case | Fit | Notes |
|---|---|---|
| TypeScript agents in Next/Node apps | Strong | Agents and workflows are plain TypeScript inside Node and Next.js apps. |
| Evals, traces, Studio | Strong | Evals, tracing and a local Studio come with the framework. |
| Python research notebooks | Poor | Mastra is TypeScript only, so notebook work in Python needs another tool. |
| Multi-agent production workflows | Strong | Typed workflow steps support branching, suspend and resume, and multi-agent runs. |
| No-code business chatbot builder | Mixed | Mastra is code-first, so business users may prefer a no-code builder. |
Review Excerpts
Excerpts from company materials and customer stories for Mastra, plus a representative buyer view drawn from public information. Paid reviews and pay-for-play sites were excluded.
“There are enrichment tools out there, but they're often too rigid. We get lists in different formats. Before Mastra, we'd have to set up different workflows every time.”
“Our agents live in the same TypeScript repo as the web app, with the same types and tests.”
Representative buyer view
“The framework is young and changes quickly, so teams should pin versions and read the release notes.”
Representative buyer view
Where customer reviews couldn't be found, our analysts attempted to give a voice to buyer sentiment, drawing on real information from review sites, forums, and product documentation.
Based on: Mastra’s pricing page and Mastra’s Series A post
Company Facts
- Founded
- 2024 (Y Combinator)
- Headquarters
- San Francisco (Y Combinator)
- Employees
- About 30 (Y Combinator)
- Accelerator
- Y Combinator, Winter 2025 batch (Y Combinator)
- Website
- mastra.ai
Key Leadership
Sam Bhagwat
Co-founder
Methodology
This page is an independent evaluation of Mastra for buyers comparing options in agent platforms & frameworks. AI Industry Reviews accepts no sponsorships, advertising, or pay-for-placement fees. Mastra did not pay for this review.
What we scored
The headline number is an Overall Score on a 0-10 scale. Eight criteria fall under it in two groups.
- Buyer outcomes (for agent platforms & frameworks)
- TypeScript agent DX
- Workflows, memory & observability
- Open-source adoption
- Hosted platform maturity
- Company & commercial
- Innovation & product leadership
- Project management & communication
- Pricing
- Contract fairness
Pricing measures whether the price looks fair for the value delivered, including packaging and renewal friction that show up in real buying cycles.
Score Composition
| Input | Weight | What it covers |
|---|---|---|
| Reviews | 40% | A proprietary read of what practitioners say about likes, complaints, and day-to-day use, including public review sites, forums, and private chat rooms. Paid reviews and pay-for-play sites are out of scope. |
| Product | 35% | Hands-on look at screens and workflows. |
| Pricing | 15% | Whether the price looks fair for what you get. |
| Docs & training | 10% | Docs, tutorials, and training material. |
How we balanced the evidence
The Overall Score is the simple average of the eight criteria. Recommendation language follows that score and the use-case matrix above.
Scope
Mastra is graded here as agent platforms & frameworks. Criteria scores can move as more review volume and product checks are added.