Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: Mastra – Open-source JS agent framework, by the developers of Gatsby

github.com

Post reply on HN
Print view View original

21–30 of 159 posts

Re: Show HN: Mastra – Open-source JS agent framework, by the developers of Gatsby

#21

Post by soulofmischief »

harliem wrote: post #13

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.

If you'd like, feel free to reach out to me via email with your requirements and we can get a conversation going. I've built a few voice agent systems in both python and JavaScript and would love to hear about what issues you're running into. Might be able to build what you need.

Re: Show HN: Mastra – Open-source JS agent framework, by the developers of Gatsby

#24

Post by swyx »

levensti wrote: post #22

Super excited to try out the new agent memory features

interesting to contrast the recent memory releases

- https://mastra.ai/docs/agents/01-agent-memory

- https://blog.langchain.dev/langmem-sdk-launch/

- https://help.getzep.com/concepts#adding-memory

not sure where all this is leading yet but glad people are exploring.

Re: Show HN: Mastra – Open-source JS agent framework, by the developers of Gatsby

#25

Post by swyx »

calcsam wrote: post #16
Gakho wrote: post #10

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.

Yeah, this is something we've heard as well. No particular feature right now but we did ship an agent in local dev to help people improve their prompts.

link to this agent?

Re: Show HN: Mastra – Open-source JS agent framework, by the developers of Gatsby

#26

Post by swyx »

bobremeika wrote: post #4

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

idk man

https://js.langchain.com/docs/introduction/

https://www.vellum.ai/products/workflows-sdk

https://github.com/transitive-bullshit/agentic

which is not to say any of them got it right or wrong, but it is by no means "missing". the big question w all of them is do they deliver enough value to last. kudos to those who at least try, of course

Re: Show HN: Mastra – Open-source JS agent framework, by the developers of Gatsby

#28

Post by calcsam »

swyx wrote: post #25
calcsam wrote: post #16

Earlier quoted context omitted.

Yeah, this is something we've heard as well. No particular feature right now but we did ship an agent in local dev to help people improve their prompts.

link to this agent?

demo: https://x.com/calcsam/status/1889856384549982419

Re: Show HN: Mastra – Open-source JS agent framework, by the developers of Gatsby

#29

Post by calcsam »

swyx wrote: post #24
levensti wrote: post #22

Super excited to try out the new agent memory features

interesting to contrast the recent memory releases - https://mastra.ai/docs/agents/01-agent-memory - https://blog.langchain.dev/langmem-sdk-launch/ - https://help.getzep.com/concepts#adding-memory not sure where all this is leading yet but glad people are exploring.

100% and agree with this, we saw the langmem stuff last night

imho getting some sort of hierarchical memory is conceptually fairly straightforward, the tricky part is having the storage and vector db pieces well integrated so that the apis are clean

Re: Show HN: Mastra – Open-source JS agent framework, by the developers of Gatsby

#30

Post by calcsam »

_1 wrote: post #27

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?

Yup! We rely on the AI SDK for model routing, and they have an Ollama provider, which will handle pretty much any local model.
Post reply on HN