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

Post by hassleblad23 » Thu, Feb 20, 2025, 7:29 PM UTC

bravura wrote: post #53

brap wrote: post #39

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 in…

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 solve the coding problem. An Editor model is given the Architect’s solution and asked to produce specific code editing instructions to apply those changes to existing source files. Splitting up “code reasoning” and “code editing” in this man…

Post by orliesaurus » Fri, Feb 21, 2025, 2:27 AM UTC

calcsam wrote: post #122

orliesaurus wrote: post #116

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

Agentic's tool library _should_ also work for Mastra via its AI SDK adapter. (We haven't tested this, so if you do try let us know if you see quirks!)

Post by anentropic » Fri, Feb 21, 2025, 10:46 AM UTC

calcsam wrote: post #143

anentropic wrote: post #132

Earlier quoted context omitted.

I think the problem is that a 'fluent' chain of calls already expresses a sequence, so the way that 'after' resets the context to start a new branch feels very awkward ... like a GOTO or something It's telling that the example relies on arbitrary indentation (which a linter will get rid of) to have some hope of comprehending it Possibly this was all motivated by a desire to avoid nested structures above all? But for…

You’re right that the syntax was inspired by the desire to avoid nested structures. But the syntax here is interesting as well and fairly readable. Worth thinking about!

    chain(llm, decider, [agentOne, agentTwo], workflow)

Post by tough » Sat, Feb 22, 2025, 10:45 AM UTC

orliesaurus wrote: post #153

calcsam wrote: post #122

Earlier quoted context omitted.

Agentic's tool library _should_ also work for Mastra via its AI SDK adapter. (We haven't tested this, so if you do try let us know if you see quirks!)

What about Toolhouse and/or composeio?

Post by ranjanprj » Sat, Feb 22, 2025, 6:11 PM UTC

Palmik wrote: post #119

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(); On a first glance, this looks like a very awkward way to represent the graph from the picture. And this is just a simple "workflow" (the structure of the graph does not depend on the results of the execution), not an agent.