Agent platforms · Tool

Mastra

Researched

Mastra is an open-source TypeScript AI agent framework, founded in 2024 by Kepler Software Inc., providing memory, tools, MCP, and observability for shipping agents from prototype to production via Studio, Agent Builder, and Server.

San Francisco Checked
Official site snapshots

See the official site at a glance

Read-only public captures of Mastra’s homepage. Screenshots are dated, never live embeds, and open full-screen.

Visit live site
Homepage · captured Jul 21, 2026
1 earlier capture
At a glance

In one minute

Start here for the decision-making essentials: what Mastra does, who it is for, how it is accessed, and the first-party sources behind this profile.

Pricing4 options

Starter plan is free at $0/month with 100K observability events, 24 CPU hours, and 15 days

Teams plan is $250/month with 1M observability events, 250 CPU hours, 6 months data retent

Starter plan is free at $0/month, including 100K observability events (+$10 per 100K addit

Teams plan is $250/month, including 1M observability events (+$8 per 100K), 250 CPU hours

Platforms
TypeScript agents frameworkTypeScript-native development approach
API accessNot public
Founded2024
AvailabilityWeb / remote
LicenseProprietary

Best suited to

Source-backed fit
TypeScript developers building AI agents and applications Teams needing to ship agents from prototype to production Organizations seeking open-source, self-hostable agent infrastructure Startups to enterprises building reliable multi-step AI workflows Customer base spans AI, FinTech, and Infrastructure categories JavaScript and TypeScript developers building AI agents
Decision support

Common questions and adoption checks

6 sourced answers

Short answers to the questions buyers and builders commonly ask about Mastra. Each answer cites the shared ledger below, where every source is listed once.

01What does Mastra say it can do?

TypeScript AI framework for building agents and applications · Provides memory, tools, MCP, and observability for shipping AI agents from prototype to pr · Agents: Define agent behavior with models, tools, memory, and instructions. · Workflows: Build durable multi-step agent processes with typed control flow.

TypeScript AI Framework for Agents and Apps
02Who is Mastra intended for?

Customer base spans AI, FinTech, and Infrastructure categories · JavaScript and TypeScript developers building AI agents

All AI FinTech Infrastructure
03What use cases does Mastra describe?

Building AI-powered applications and agents that reason, remember, and act in TypeScript · Building AI agents · Framework for building AI applications and agents on a modern TypeScript stack · Building AI agents, workflows, and TypeScript tooling

Ship AI agents that reason, remember, and act in TypeScript.
04What pricing information is available for Mastra?

Starter plan is free at $0/month with 100K observability events, 24 CPU hours, and 15 days · Teams plan is $250/month with 1M observability events, 250 CPU hours, 6 months data retent · Starter plan is free at $0/month, including 100K observability events (+$10 per 100K addit · Teams plan is $250/month, including 1M observability events (+$8 per 100K), 250 CPU hours

Starter Free for everyone $0 / month Observability events 100K events + $10/100K CPU time 24 CPU hours + $0.35/hr Data retention 15 days
05What integrations does Mastra document?

Supports models specified as provider/model strings, e.g. openai/gpt-5.5 (OpenAI format: o · Supported LLM providers: OpenAI, Anthropic, Google, xAI · Replit's Agent 3 automatically generates Mastra agents and workflows from natural language

Define model as a string in provider/model format, for example openai/gpt-5.5 . For OpenAI, use openai/<model> , not openai:<model> , and don't import or pass a provider object.
06How can Mastra be deployed or accessed?

Quickstart via CLI command 'npm create mastra' · Supported deployment targets: Amazon Bedrock AgentCore, Amazon EC2, AWS Lambda, Azure App · Cloud computing service · Cloud deployment for agents

npm create mastra
Decision guide

Capabilities and operating fit

Agent platforms

This profile connects the jobs Mastra is described as handling with its delivery model, access options and the subjects used to match it to related products in this directory.

Common use cases

  • Building AI-powered applications and agents that reason, remember, and act in TypeScript
  • Creating durable multi-step agent processes with typed control flow
  • Cloud or self-hosted deployment of agents across multiple platforms
  • Collaborating, evaluating, and iterating on agents with a Studio interface
  • Building AI agents
  • Framework for building AI applications and agents on a modern TypeScript stack

Access signals

Pricing model
Starter plan is free at $0/month with 100K observability events, 24 CPU hours, and 15 days · Teams plan is $250/month with 1M observability events, 250 CPU hours, 6 months data retent · Starter plan is free at $0/month, including 100K observability events (+$10 per 100K addit · Teams plan is $250/month, including 1M observability events (+$8 per 100K), 250 CPU hours
API
Not publicly listed
Source links
15 recorded
Source-backed

Verified facts

Updated July 22, 2026

Each fact points to a recorded source, making it easy to distinguish verified product information from claims that need checking.

Official website

HTTP 200 verified twice

First-party description

TypeScript AI Framework for Agents and Apps | Mastra

Source-supported facts

TypeScript AI Framework for Agents and Apps · Founded in 2024 by Kepler Software Inc. · Provides memory, tools, MCP, and observability to go from prototype to production

Capability

TypeScript AI framework for building agents and applications

Capability

Provides memory, tools, MCP, and observability for shipping AI agents from prototype to production

Use case

Building AI-powered applications and agents that reason, remember, and act in TypeScript

Platform

Includes Studio (collaborate, evaluate, iterate), Agent Builder (collaborate, evaluate, iterate), and Server (cloud deployment for agents)

Deployment

Quickstart via CLI command 'npm create mastra'

View 32 more verified facts
Capability

Agents: Define agent behavior with models, tools, memory, and instructions.

[7]mastra.ai/pricing
Capability

Workflows: Build durable multi-step agent processes with typed control flow.

[7]mastra.ai/pricing
Capability

Observational Memory: Persist conversation context and application state across sessions.

[7]mastra.ai/pricing
Pricing

Starter plan is free at $0/month with 100K observability events, 24 CPU hours, and 15 days data retention.

[7]mastra.ai/pricing
Pricing

Teams plan is $250/month with 1M observability events, 250 CPU hours, 6 months data retention, and includes multiple teams, SSO, and SOC 2 docs.

[7]mastra.ai/pricing
Open source

Mastra is available under the Apache 2.0 license for self-hosted use.

[7]mastra.ai/pricing
Capability

TypeScript framework for building AI agents

[3]mastra.ai/docs
Use case

Building AI agents

[3]mastra.ai/docs
Platform

Node.js / TypeScript (ES2022 modules), installed via npm

[3]mastra.ai/docs
Integration

Supports models specified as provider/model strings, e.g. openai/gpt-5.5 (OpenAI format: openai/<model>)

[3]mastra.ai/docs
Capability

Tools must be defined via createTool() with id, description, inputSchema (zod), and execute()

[3]mastra.ai/docs
Capability

Agents are created via the Agent class from @mastra/core/agent with {id, name, instructions, model}

[3]mastra.ai/docs
Use case

Framework for building AI applications and agents on a modern TypeScript stack

[2]mastra.ai/guides/getting-started/quickstart
Integration

Supported LLM providers: OpenAI, Anthropic, Google, xAI

[2]mastra.ai/guides/getting-started/quickstart
Capability

Default agent harness includes workspace tools, memory, task tracking, web access, schedules, storage, and observability

[2]mastra.ai/guides/getting-started/quickstart
Platform

Mastra Studio local UI runs at http://localhost:4111 for building, testing, and managing agents, workflows, and tools

[2]mastra.ai/guides/getting-started/quickstart
Deployment

Supported deployment targets: Amazon Bedrock AgentCore, Amazon EC2, AWS Lambda, Azure App Services, Cloudflare, Digital Ocean, Inngest, Mastra platform, Netlify, Temporal, Vercel

[2]mastra.ai/guides/getting-started/quickstart
Platform

Integrates with web and Node frameworks: Next.js, React, Astro, SvelteKit, Nuxt, Express, NestJS, Hono, Electron

[2]mastra.ai/guides/getting-started/quickstart
Company

Kepler Software Inc

[10]mastra.ai/privacy-policy
Deployment

Cloud computing service

[10]mastra.ai/privacy-policy
Capability

Build agents and workflows

[10]mastra.ai/privacy-policy
Capability

Observability — metrics, logs, traces

[10]mastra.ai/privacy-policy
Capability

Collaborate, evaluate, iterate

[10]mastra.ai/privacy-policy
Deployment

Cloud deployment for agents

[10]mastra.ai/privacy-policy
Capability

Build agents and workflows via a Framework product

[5]mastra.ai/customers
Capability

Provides observability through metrics, logs, and traces

[5]mastra.ai/customers
Deployment

Offers a Server product for cloud deployment of agents

[5]mastra.ai/customers
Platform

Studio enables teams to collaborate, evaluate, and iterate on agents

[5]mastra.ai/customers
Audience

Customer base spans AI, FinTech, and Infrastructure categories

[5]mastra.ai/customers
Company

Trusted by thousands of organizations ranging from startups to major enterprises

[5]mastra.ai/customers
Company

Mastra

[8]mastra.ai/about
Founded

2024

[8]mastra.ai/about
Practical capabilities

What it helps with

8 documented areas

A concise view of the jobs, capabilities and integrations described in the recorded product sources.

Use case

Building AI-powered applications and agents that reason, remember, and act in TypeScript

Use case

Creating durable multi-step agent processes with typed control flow

Use case

Cloud or self-hosted deployment of agents across multiple platforms

Use case

Collaborating, evaluating, and iterating on agents with a Studio interface

Use case

Building AI agents

Use case

Framework for building AI applications and agents on a modern TypeScript stack

Use case

Building AI agents, workflows, and TypeScript tooling

Use case

Sanity leveraged Mastra to build a CMS-native content agent that understands, creates, and

Availability

Where it runs and where to get it

Source checked

Documented product formats, platforms and official distribution destinations. Availability can vary by region and plan.

Cost / license

Starter plan is free at $0/month with 100K observability events, 24 CPU hours, and 15 days · Teams plan is $250/month with 1M observability events, 250 CPU hours, 6 months data retent · Starter plan is free at $0/month, including 100K observability events (+$10 per 100K addit · Teams plan is $250/month, including 1M observability events (+$8 per 100K), 250 CPU hours Mastra is available under the Apache 2.0 license for self-hosted use. · Yes

Platforms

Includes Studio (collaborate, evaluate, iterate), Agent Builder (collaborate, evaluate, itNode.js / TypeScript (ES2022 modules), installed via npmMastra Studio local UI runs at http://localhost:4111 for building, testing, and managing aIntegrates with web and Node frameworks: Next.js, React, Astro, SvelteKit, Nuxt, Express, Studio enables teams to collaborate, evaluate, and iterate on agentsTypeScript agents frameworkTypeScript-native development approach
Implementation details

Adoption notes

DeploymentQuickstart via CLI command 'npm create mastra' · Supported deployment targets: Amazon Bedrock AgentCore, Amazon EC2, AWS Lambda, Azure App · Cloud computing service · Cloud deployment for agents
LicenseMastra is available under the Apache 2.0 license for self-hosted use. · Yes
Model supportNot disclosed by source
Data controlSOC 2 compliance is included on the Teams plan (and above). · Team plan includes SSO and supports multiple teams
Learning curveIntermediate
Primary use casesBuilding AI-powered applications and agents that reason, remember, and act in TypeScript, Creating durable multi-step agent processes with typed control flow, Cloud or self-hosted deployment of agents across multiple platforms, Collaborating, evaluating, and iterating on agents with a Studio interface, Building AI agents, Framework for building AI applications and agents on a modern TypeScript stack, Building AI agents, workflows, and TypeScript tooling, Sanity leveraged Mastra to build a CMS-native content agent that understands, creates, and, Used by SoftBank as an AI agent framework to build the Satto Workspace platform that trans, Building AI agents inside a platform that maintain strict permission controls and prevent

What to verify before adopting

    Evolution and major updates

    Mastra timeline

    A concise history of software releases and material product changes. Events appear only when a dated source supports what changed.

    Research in progress
    Scheduled for research

    Building a reliable release history.

    This profile is being checked for dated releases and material product changes. Nothing appears here until the exact date and event can be verified from a recorded source.

    Dated event Short explanation Original source
    Citation ledger

    Recorded sources

    15 unique pages

    Facts, answers, structured details, milestones and primary resource links cite this shared ledger. Each external page appears once; release tags from the same GitHub project are grouped under one release history.

    1. 1mastra.ai 9 facts · 3 answers · Official site
    2. 2mastra.ai/guides/getting-started/quickstart 6 facts · 4 answers · Official site
    3. 3mastra.ai/docs 6 facts · 3 answers · Documentation
    4. 4mastra.ai/blog 6 facts · 2 answers · Official site
    5. 5mastra.ai/customers 6 facts · 2 answers · Official site
    6. 6mastra.ai/customers/replit 7 facts · 1 answer · Official site
    7. 7mastra.ai/pricing 6 facts · 2 answers · Pricing
    8. 8mastra.ai/about 6 facts · 1 answer · Official site
    9. 9mastra.ai/platform-observability 6 facts · 1 answer · Official site
    10. 10mastra.ai/privacy-policy 6 facts · 1 answer · Security
    11. 11mastra.ai/blog/mastra-platform-pricing 5 facts · 1 answer · Pricing
    12. 12mastra.ai/customers/factorial 6 facts · Official site
    13. 13mastra.ai/customers/sanity 6 facts · Official site
    14. 14mastra.ai/customers/softbank 6 facts · Official site
    15. 15mastra.ai/customers/workos 6 facts · Official site
    Research status91 substantive facts · 15 source pages · quality score 91/100