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

Show HN: Agno – A full-stack framework for building Multi-Agent Systems

github.com

Post reply on HN
Print view View original

11–20 of 23 posts

Re: Show HN: Agno – A full-stack framework for building Multi-Agent Systems

#11

Post by maxtermed »

onebitwise wrote: post #3

I feel the cookbook is a little messy. I would love to see an example using collaborative agents, like an editorial team that write articles based on searches and expert of topics (just as example) Can be better to have a different repo for examples? Btw great project! Kudos

Good point. The cookbook can be hard to navigate right now, but that's mostly because the team is putting out a tremendous amount of work and updating things constantly, which is a good problem to have.

This example might be close to what you're describing: https://github.com/agno-agi/agno/blob/main/cookbook/workflow...

It chains agents for web research, content extraction, and writing with citations.

I used it as a starting point for a couple projects that are now in production. It helped clarify how to structure workflows.

Re: Show HN: Agno – A full-stack framework for building Multi-Agent Systems

#12

Post by maxtermed »

I've been using this framework for a while, it's really solid IMO. It abstracts just enough to make building reliable agents straightforward, but still leaves lots of room for customization.

The way agent construction is laid out (with a clear path for progressively adding tools, memory, knowledge, storage, etc.) feels very logical.

Definitely lowered the time it takes to get something working.

Re: Show HN: Agno – A full-stack framework for building Multi-Agent Systems

#14

Post by gkapur »

JimDabell wrote: post #2

> At Agno, we're obsessed with performance. Why? because even simple AI workflows can spawn thousands of Agents. Scale that to a modest number of users and performance becomes a bottleneck. This strikes me as odd. Aren’t all these agents pushing tokens through LLMs? The number of milliseconds needed to instantiate a Python object and the number of kilobytes it takes up in memory seem irrelevant in this context.

If you are running things locally (I would think especially on the edge, whether on not the LLM is local or in the cloud) this would matter. Or if you are running some sort of agent orchestration where the output of LLMs is streaming it could possibly matter?

Re: Show HN: Agno – A full-stack framework for building Multi-Agent Systems

#15

Post by bediashpreet »

idan707 wrote: post #9

Over the past few months, I've transitioned to using Agno in production, and I have to say, the experience has been nothing short of fantastic. A huge thank you for creating such an incredible framework!

Thank you for the kind words <3

Re: Show HN: Agno – A full-stack framework for building Multi-Agent Systems

#18

Post by bediashpreet »

maxtermed wrote: post #12

I've been using this framework for a while, it's really solid IMO. It abstracts just enough to make building reliable agents straightforward, but still leaves lots of room for customization. The way agent construction is laid out (with a clear path for progressively adding tools, memory, knowledge, storage, etc.) feels very logical. Definitely lowered the time it takes to get something working.

Thank you for using Agno and the kind words!

Re: Show HN: Agno – A full-stack framework for building Multi-Agent Systems

#19

Post by bediashpreet »

onebitwise wrote: post #3

I feel the cookbook is a little messy. I would love to see an example using collaborative agents, like an editorial team that write articles based on searches and expert of topics (just as example) Can be better to have a different repo for examples? Btw great project! Kudos

Thank you for the feedback and the kind words.

Agree that the cookbooks have gotten messy. Not an excuse but sharing the root case behind it: we're building very, very fast and putting examples out for users quickly. We maintain backwards compatibility so sometimes you see 2 examples doing the same thing.

I'll make it a point to clean up the cookbooks and share more examples under this comment. Here are 2 to get started:

- Content creator team: https://github.com/agno-agi/agno/blob/main/cookbook/examples...

- Blog post generator workflow: https://github.com/agno-agi/agno/blob/main/cookbook/workflow...

Both are easily extensible. Always available for feedback at ashpreet[at]agno[dot]com

Re: Show HN: Agno – A full-stack framework for building Multi-Agent Systems

#20

Post by bediashpreet »

JimDabell wrote: post #2

> At Agno, we're obsessed with performance. Why? because even simple AI workflows can spawn thousands of Agents. Scale that to a modest number of users and performance becomes a bottleneck. This strikes me as odd. Aren’t all these agents pushing tokens through LLMs? The number of milliseconds needed to instantiate a Python object and the number of kilobytes it takes up in memory seem irrelevant in this context.

You’re right, inference is typically the bottleneck and it’s reasonable to think the framework’s performance might not be critical. But here’s why we care deeply about it:

- High Performance = Less Bloat: As a software engineer, I value lean, minimal-dependency libraries. A performant framework means the authors have kept the underlying codebase lean and simple. For example: with Agno, the Agent is the base class and is 1 file, whereas with LangChain you'll get 5-7 layers of inheritance. Another example: when you install crewai, it installs the kubernetes library (along with half of pypi). Agno comes with a very small (i think - While inference is one part of the equation, parallel tool executions, async knowledge search and async memory updates improve the entire system's performance. Because we're focused on performance, you're guaranteed top of the line experience without thinking about it, its a core part of our philosophy.

- Milliseconds Matter: When deploying agents in production, you’re often instantiating one or even multiple agents per request (to limit data and resource access). At moderate scale, like 10,000 requests per minute, even small delays can impact user experience and resource usage.

- Scalability and Cost Efficiency: High-performance frameworks help reduce infrastructure costs, enabling smoother scaling as your user base grows.

I'm not sure why you would NOT want a performant library, sure inference is a part of it (which isn't in our control) but I'd definitely want to use libraries from engineers that value performance.

Post reply on HN