LmCast :: Stay tuned in

Show HN: Mastra 1.0, open-source JavaScript agent framework from the Gatsby devs

Recorded: Jan. 21, 2026, 11:03 a.m.

Original Summarized

GitHub - mastra-ai/mastra: From the team behind Gatsby, Mastra is a framework for building AI-powered applications and agents with a modern TypeScript stack.

Skip to content

Navigation Menu

Toggle navigation

Sign in

Appearance settings

PlatformAI CODE CREATIONGitHub CopilotWrite better code with AIGitHub SparkBuild and deploy intelligent appsGitHub ModelsManage and compare promptsMCP RegistryNewIntegrate external toolsDEVELOPER WORKFLOWSActionsAutomate any workflowCodespacesInstant dev environmentsIssuesPlan and track workCode ReviewManage code changesAPPLICATION SECURITYGitHub Advanced SecurityFind and fix vulnerabilitiesCode securitySecure your code as you buildSecret protectionStop leaks before they startEXPLOREWhy GitHubDocumentationBlogChangelogMarketplaceView all featuresSolutionsBY COMPANY SIZEEnterprisesSmall and medium teamsStartupsNonprofitsBY USE CASEApp ModernizationDevSecOpsDevOpsCI/CDView all use casesBY INDUSTRYHealthcareFinancial servicesManufacturingGovernmentView all industriesView all solutionsResourcesEXPLORE BY TOPICAISoftware DevelopmentDevOpsSecurityView all topicsEXPLORE BY TYPECustomer storiesEvents & webinarsEbooks & reportsBusiness insightsGitHub SkillsSUPPORT & SERVICESDocumentationCustomer supportCommunity forumTrust centerPartnersOpen SourceCOMMUNITYGitHub SponsorsFund open source developersPROGRAMSSecurity LabMaintainer CommunityAcceleratorArchive ProgramREPOSITORIESTopicsTrendingCollectionsEnterpriseENTERPRISE SOLUTIONSEnterprise platformAI-powered developer platformAVAILABLE ADD-ONSGitHub Advanced SecurityEnterprise-grade security featuresCopilot for BusinessEnterprise-grade AI featuresPremium SupportEnterprise-grade 24/7 supportPricing

Search or jump to...

Search code, repositories, users, issues, pull requests...

Search

Clear

Search syntax tips

Provide feedback


We read every piece of feedback, and take your input very seriously.

Include my email address so I can be contacted

Cancel

Submit feedback

Saved searches

Use saved searches to filter your results more quickly

Name

Query

To see all available qualifiers, see our documentation.

Cancel

Create saved search

Sign in

Sign up

Appearance settings

Resetting focus

You signed in with another tab or window. Reload to refresh your session.
You signed out in another tab or window. Reload to refresh your session.
You switched accounts on another tab or window. Reload to refresh your session.

Dismiss alert

mastra-ai

/

mastra

Public

Notifications
You must be signed in to change notification settings

Fork
1.4k

Star
19.8k

From the team behind Gatsby, Mastra is a framework for building AI-powered applications and agents with a modern TypeScript stack.

mastra.ai

License

View license

19.8k
stars

1.4k
forks

Branches

Tags

Activity

Star

Notifications
You must be signed in to change notification settings

Code

Issues
143

Pull requests
157

Actions

Projects
1

Security

Uh oh!

There was an error while loading. Please reload this page.


Insights

Additional navigation options

Code

Issues

Pull requests

Actions

Projects

Security

Insights

mastra-ai/mastra

 mainBranchesTagsGo to fileCodeOpen more actions menuFolders and filesNameNameLast commit messageLast commit dateLatest commit History12,284 Commits.changeset.changeset  .claude.claude  .cursor.cursor  .dev.dev  .github.github  .husky.husky  .opencode/command.opencode/command  authauth  bookbook  client-sdksclient-sdks  communicationscommunications  deployersdeployers  docsdocs  e2e-testse2e-tests  examplesexamples  explorationsexplorations  observabilityobservability  packagespackages  patchespatches  pubsub/google-cloud-pubsubpubsub/google-cloud-pubsub  scriptsscripts  server-adaptersserver-adapters  storesstores  templatestemplates  voicevoice  workflowsworkflows  .coderabbit.yaml.coderabbit.yaml  .gitignore.gitignore  .prettierignore.prettierignore  .prettierrc.prettierrc  .vercelignore.vercelignore  .windsurfrules.windsurfrules  CLAUDE.mdCLAUDE.md  CODE_OF_CONDUCT.mdCODE_OF_CONDUCT.md  CONTRIBUTING.mdCONTRIBUTING.md  DEVELOPMENT.mdDEVELOPMENT.md  LICENSE.mdLICENSE.md  README.mdREADME.md  package.jsonpackage.json  pnpm-lock.yamlpnpm-lock.yaml  pnpm-workspace.yamlpnpm-workspace.yaml  renovate.jsonrenovate.json  tsconfig.build.jsontsconfig.build.json  tsconfig.jsontsconfig.json  tsconfig.node.jsontsconfig.node.json  turbo.jsonturbo.json  vitest.config.observability.tsvitest.config.observability.ts  vitest.config.tsvitest.config.ts  View all filesRepository files navigationREADMECode of conductContributingLicenseMastra

Mastra is a framework for building AI-powered applications and agents with a modern TypeScript stack.
It includes everything you need to go from early prototypes to production-ready applications. Mastra integrates with frontend and backend frameworks like React, Next.js, and Node, or you can deploy it anywhere as a standalone server. It's the easiest way to build, tune, and scale reliable AI products.
Why Mastra?
Purpose-built for TypeScript and designed around established AI patterns, Mastra gives you everything you need to build great AI applications out-of-the-box.
Some highlights include:

Model routing - Connect to 40+ providers through one standard interface. Use models from OpenAI, Anthropic, Gemini, and more.

Agents - Build autonomous agents that use LLMs and tools to solve open-ended tasks. Agents reason about goals, decide which tools to use, and iterate internally until the model emits a final answer or an optional stopping condition is met.

Workflows - When you need explicit control over execution, use Mastra's graph-based workflow engine to orchestrate complex multi-step processes. Mastra workflows use an intuitive syntax for control flow (.then(), .branch(), .parallel()).

Human-in-the-loop - Suspend an agent or workflow and await user input or approval before resuming. Mastra uses storage to remember execution state, so you can pause indefinitely and resume where you left off.

Context management - Give your agents the right context at the right time. Provide conversation history, retrieve data from your sources (APIs, databases, files), and add human-like working and semantic memory so your agents behave coherently.

Integrations - Bundle agents and workflows into existing React, Next.js, or Node.js apps, or ship them as standalone endpoints. When building UIs, integrate with agentic libraries like Vercel's AI SDK UI and CopilotKit to bring your AI assistant to life on the web.

MCP servers - Author Model Context Protocol servers, exposing agents, tools, and other structured resources via the MCP interface. These can then be accessed by any system or agent that supports the protocol.

Production essentials - Shipping reliable agents takes ongoing insight, evaluation, and iteration. With built-in evals and observability, Mastra gives you the tools to observe, measure, and refine continuously.

Get started
The recommended way to get started with Mastra is by running the command below:
npm create mastra@latest
Follow the Installation guide for step-by-step setup with the CLI or a manual install.
If you're new to AI agents, check out our templates, course, and YouTube videos to start building with Mastra today.
Documentation
Visit our official documentation.
MCP Servers
Learn how to make your IDE a Mastra expert by following the @mastra/mcp-docs-server guide.
Contributing
Looking to contribute? All types of help are appreciated, from coding to testing and feature specification.
If you are a developer and would like to contribute with code, please open an issue to discuss before opening a Pull Request.
Information about the project setup can be found in the development documentation
Support
We have an open community Discord. Come and say hello and let us know if you have any questions or need any help getting things running.
It's also super helpful if you leave the project a star here at the top of the page
Security
We are committed to maintaining the security of this repo and of Mastra as a whole. If you discover a security finding
we ask you to please responsibly disclose this to us at security@mastra.ai and we will get
back to you.

About

From the team behind Gatsby, Mastra is a framework for building AI-powered applications and agents with a modern TypeScript stack.

mastra.ai

Topics

nodejs

javascript

typescript

ai

reactjs

mcp

nextjs

tts

chatbots

workflows

agents

llm

evals

Resources

Readme

License

View license

Code of conduct

Code of conduct

Contributing

Contributing

Uh oh!

There was an error while loading. Please reload this page.


Activity

Custom properties
Stars

19.8k
stars
Watchers

84
watching
Forks

1.4k
forks

Report repository

Releases
68

January 20, 2026

Latest

Jan 21, 2026


+ 67 releases

Used by 2k

+ 2,001

Contributors
313

Uh oh!

There was an error while loading. Please reload this page.


+ 299 contributors

Languages

TypeScript
99.2%

Other
0.8%

Footer

© 2026 GitHub, Inc.

Footer navigation

Terms

Privacy

Security

Status

Community

Docs

Contact

Manage cookies

Do not share my personal information

You can’t perform that action at this time.

Mastra, developed by the team behind Gatsby, represents a framework designed for constructing AI-powered applications and agents utilizing a modern TypeScript stack. The project aims to simplify the process of building, tuning, and scaling reliable AI products. Key features include model routing allowing connection to over 40 AI providers (OpenAI, Anthropic, Gemini, and more), autonomous agents capable of reasoning and tool usage, graph-based workflow engines for complex multi-step processes, and human-in-the-loop capabilities for pausing and resuming agent or workflow execution with user input. Mastra also emphasizes context management, providing agents with relevant information at the appropriate time, along with integrations for deploying agents and workflows within existing React, Next.js, or Node.js applications. The framework incorporates MCP servers to expose agents and tools via a standardized protocol and emphasizes production essentials with built-in evaluation and observability tools.

The framework's intention is to provide developers with an out-of-the-box solution, streamlining the creation of AI applications. It promotes the use of TypeScript, a popular and robust language, for development. Central to its design is the ability to build autonomous agents that can independently solve tasks. These agents can leverage LLMs (Large Language Models) and a range of tools, iterating internally to arrive at a final answer or reach a predefined stopping condition. Workflows enable developers to orchestrate complex processes through intuitive, graph-based syntax (using `.then()`, `.branch()`, and `.parallel()` for control flow). The human-in-the-loop feature provides a mechanism to introduce human intervention, pausing execution and awaiting user input before resuming. Context management is handled by providing agents with complete conversational histories and the ability to retrieve data from various sources—APIs, databases, and files—fostering coherent and consistent agent behavior.

From a technological perspective, Mastra supports the creation and deployment of MCP servers – Model Context Protocol servers, which serve as a foundation for inter-agent communication. The project also acknowledges the importance of ongoing assessment, evaluation, and refinement, integrating metrics and monitoring into the development process through its built-in evaluation and observability tools. Mastra’s architecture is designed to be adaptable, supported by integration capabilities with frontend and backend frameworks, facilitating seamless deployment and scaling. Getting started with Mastra involves running `npm create mastra@latest` and following the provided installation guide. The project actively supports open-source contributions and maintains an engaged community through a Discord channel. Furthermore, it includes a commitment to security, addressing vulnerabilities and encouraging responsible disclosure.