Mastra
AI
agent framework
SHOW HN2025
How HN took it
16 positive, 44 neutral or asking, 1 mixed, 24 critical, out of 85 comments about the project. Thread score -0.01.
Idea: 1 for, 10 againstDesign: 2 for, 5 againstPricing: 0 for, 3 againstExecution: 1 for, 1 againstPerformance: 0 for, 1 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Clear, easy-to-use abstractions with low-level control when needed
From 1 comment
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…
alanwells on HN
Better than LangChain for the commenter's needs
From 1 comment
You’re awesome guys! I had so many problems with lanchain and am very happy since switching to Mastra
yovboy on HN
Objections
Elastic v2 license is not truly open source
From 1 comment
"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…
fuddle on HN
Workflow syntax with chained step/then/after is awkward to read
From 2 comments
The example from the landing page does not exactly spark joy: ``` testWorkflow .step(llm) .then(decider) .then(agentOne) .then(workflow) .after(decider) .then(agentTwo)…
Palmik on HNI think it is just easier to comprehend if the edges/dependencies are explicit (as an array for example).
jumski on HN
Many similar agent frameworks already exist; the framework covers only a small part of the work
From 1 comment
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…
_pdp_ on HN
Built on JavaScript, which is the wrong runtime for agents
From 1 comment
I agree, and it feels like JS is just the wrong runtime for agents. Really languages that can model state in sane ways and have a good concurrency story like Elixir make much…
cpursley on HN
Requests
Python support
From 1 comment
Any timeline for python?
gregpr07 on HN
Automatic step retries with backoff
From 1 comment
Are there any plans to add automatic retries for individual steps (with configurable max attempts and backoff strategy)?
monideas on HN
Websocket support
From 1 comment
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,…
lmrl on HN
SSE MCP server support
From 1 comment
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]…
joshstrange on HN
Explicit edges or dependencies in workflow graphs
From 2 comments
I think it is just easier to comprehend if the edges/dependencies are explicit (as an array for example).
jumski on HNWe have a ticket to allow this actually!
calcsam on HN
Questions
What are agents actually for compared with a single LLM call
From 2 comments
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…
brap on HNI don't work in prompt engineering but my partner does and she tells me numerous need for agents in cases where you want some technology which goes and seeks things on the live…
2pointsomone on HN
Voice agent support
From 2 comments
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…
harliem on HNWe're just starting to do that and have a few TTS providers: ElevenLabs, OpenAI, PlayAI. We hear a lot from people who are outgrowing the voice agent platforms and moving to…
calcsam on HN
When to start writing evals
From 2 comments
Congrats on launching! Curious how early the Mastra team thinks people should be thinking about evals and setting up a pipeline for them.
aranibatta on HNWe tend to recommend folks spend a few hours writing evals after they spend a couple weeks prototyping. Then they get a sense of how valuable evals are for their use-case. We…
calcsam on HN
Alternatives named
LangChain
From 2 comments
You’re awesome guys! I had so many problems with lanchain and am very happy since switching to Mastra
yovboy on HNTrue. That's the reason I see a lot of people dropping similar frameworks like LangChain recently:…
fsndz on HN
LangGraph
From 1 comment
Couldn't agree more. This also looks mostly like a Typescript "port" of Langgraph, and I say "port" because Langgraph has a TS framework already.
incanspyder on HN
Vercel AI SDK
From 1 comment
i was using vercel ai sdk for my production app and it was such a bad experience that I eventually went with native implementation and tbh it was not much of work thanks to…
jerrygoyal on HN
Instructor
From 1 comment
True. That's the reason I see a lot of people dropping similar frameworks like LangChain recently:…
fsndz on HN
Aider architect/editor approach
From 1 comment
https://aider.chat/2024/09/26/architect.html "Aider now has experimental support for using two models to complete each coding task: An Architect model is asked to describe how to…
bravura on HN