The example from the landing page does not exactly spark joy:

    testWorkflow
     .step(llm)
       .then(decider)
       .then(agentOne)
       .then(workflow)
     .after(decider)
       .then(agentTwo)
       .then(workflow)
      .commit();

Very excited about Mastra! We have a number of Agent-ic things we'll be building at ElectricSQL and Mastra looks like a breath of fresh air.

Also the team is top-notch — Sam was my co-founder at Gatsby and I worked closely with Shane and Abhi and I have a ton of confidence in their product & engineering abilities.

This looks awesome! Quick question, are there plans to support SSE MCP servers? I see Stdio [0] are supported and I can always run a proxy but SSE would be awesome.

[0] https://mastra.ai/docs/reference/tools/client

Happy Mastra user here! Strikes the right balance between letting me build with higher level abstractions but providing lower level controls when needed. I looked at a handful of other frameworks before getting started and the clarity & easy of use of Mastra stood out. Nice work.

I don’t really understand agents. I just don’t get why we need to pretend we have multiple personalities, especially when they’re all using the same model.

Can anyone please give me a usecase, that couldn’t be solved with a single API call to a modern LLM (capable of multi-step planning/reasoning) and a proper prompt?

Or is this really just about building the prompt, and giving the LLM closer guidance by splitting into multiple calls?

I’m specifically not asking about function calling.

Congrats on launching. I've noticed that switching prompts without edits between different LLM providers has degradation on performance. I'm wondering if you guys have noticed how developers do these "translations", I'm wondering since maybe your eval framework might have data for best practices.

By the developers of Gatsby is a minus, not a plus makes me think this is going to be the next abandonware.

I don't want to be that person but there are hundreds of other similar frameworks doing more or less the same thing. Do you know why? Because writing a framework that orchestrates a number of tools with a model is the easy part. In fact, most of the time you don't even need a framework. All of these framework focus on the trivial and you can tell that simply by browsing the examples section.

This is like 5% of the work. The developer needs to fill the other 95% which involves a lot more things that are strictly outside of scope of the framework.

Impressive. Have you seen any success with Mastra being used to build voice agents? Our company has been experimenting with VAPI, which just launched a workflow builder into open beta (https://docs.vapi.ai/workflows), but it has a lot of rough edges.

I basically learned everything about how agents work by using Mastra's framework and going through their documentation. The founders are also super hands-on and love to help!

Congrats on launching! Curious how early the Mastra team thinks people should be thinking about evals and setting up a pipeline for them.

This looks really great! How do you make money? Do you charge for deploying these to your platform? I couldnt find anything on pricing

Are there any plans to add automatic retries for individual steps (with configurable max attempts and backoff strategy)?

Why is it on top of Vercel’s platform?

I created a similar library for orchestrations, but it’s more explicit and lightweight. https://github.com/langtail/ai-orchestra

Congrats, looks promising! 1. Is it possible to create custom endpoints? I see that several endpoints are created when running “mastra dev”.

2. Related to previous question, since this is node based, is it possible to support websockets?

Does Mastra support libraries of tools for agents like toolhouse.ai or https://github.com/transitive-bullshit/agentic

Congrats! Side question - is the website OS as well? I'd like to "borrow" the Nav Bar code. I looked on GitHub and couldn't find it in the repos and 300+ branches. Cheers!

i am very long on TS as the future of agent applications. nice work team

This looks really nice. We've been considering developing something very similar in-house. Are you guys looking at supporting MLC Web LLM, or someother local models?

Congrats! This is exactly what the AI world needs. I'm thinking about using Mastra for a class I'm working on with AI Agents.

I thought Kyle Matthews was the creator of Gatsby

Do the workflows support voice-to-voice models like openai's realtime? Or if something like that exists I'd be curios.

Interested to learn more about the PDF -> CAD project built on mastra, can you share a link?

Neat, I’m going to use this

Got excited, was hoping to see a repository of Go Agents.

Super excited to try out the new agent memory features

Congrats guys! really excited to try this out!

Kudos on using XState!

Any timeline for python?

"You may not provide the software to third parties as a hosted or managed service" - The Elastic v2 license isn't actually open source like your title mentions: "Open-source JS agent framework"

https://github.com/mastra-ai/mastra/blob/main/LICENSE

> Mastra uses the Vercel AI SDK

It started off wrong.

Bamfs

Very interesting set of abstractions that address lots of the pain points when building agents, also the team is super eager to help out!

You’re awesome guys! I had so many problems with lanchain and am very happy since switching to Mastra

A TypeScript first AI framework is something that has been missing. How do you work with AI SDK?