This benchmark is so weird 2 metrics are basically the same 3 metrics are not framework dependent The remaining one is installation effort It feels like people don't know how to use those frameworks other than the getting started...
This was really helpful. Thanks. Are there any differences in the tools available between them? For example when I tried crewAI - it couldn’t do instagram scraping. Wondering if others offer better more rich tools that can invoked easily. For reference - l’m a newbie coder.
Thank you. Instagram scraping is very challenging, as they dont like it that much :D. Yes all those tools, have different use cases. And they evolve a lot and very fast. Probably I will do a new video soon.
Your ease of use VS instalation complexity is misleading. The ease of use trait should have it's maximum on the right as that's the established way to present it, yet "easy" is on the left side
Where is agency swarm ? If you want fast, use groq, if you want cheap use ollama, if you need something done like this kind of research, speed does not matter, but insightfull results do. So improve prompt and or use better model. If you cant code, dont use ai frameworks, there zare plenty of other options now, or was opensource a requirement ?
Yes, thats true, of course speed is not a requirement for this task, just wanted to compare the different kpi, then everyon has to choose the framework what fits best for a specific use case.
Thanks for the video but there is something I don’t understand in this « benchmark ». What about the frameworks « output » ?? Does all the frameworks generated exactly the same final report ? I guess not ? Then for a « benchmark » to be meaningful I think it should includes a careful rating of the results. Why would I pick a framework that it slightly faster or easier to install if the produced results are poorer ?? Or did I miss something ?? Many thanks for your thoughts on that…
thats a good point, thank you, the results where actually very similar indeed, but not exactly the same, I will definitely consider it for my next benchmark
Man , your picture have a better place, move it to the bottom left corner, , it is already to much big and cover your content. please shrink ur self 50% and move to the left, or even better hide it , it has no value to the video.
![AI Agent Framework Battle: CrewAI vs. AutoGen vs. LangGraph vs Agent Zero | Underdog Triumphs? [4/5]](http://i.ytimg.com/vi/iSRKlR9VxCo/mqdefault.jpg)
Thanks! Would you be up for comparing others? I am specifically interested in Swarm, pydantic ai, smolagents and griptape ai?
Great content thank you!
Fyi, you can combine langgraph with crewai too
Ah really? Did not know that, did you try it? How were your results?
@@FlorenzErstlingI have not myself, but I believe one of the examples in the example repo does that
I got the same impression, AutoGen is great
This benchmark is so weird
2 metrics are basically the same
3 metrics are not framework dependent
The remaining one is installation effort
It feels like people don't know how to use those frameworks other than the getting started...
This was really helpful. Thanks. Are there any differences in the tools available between them? For example when I tried crewAI - it couldn’t do instagram scraping. Wondering if others offer better more rich tools that can invoked easily. For reference - l’m a newbie coder.
Thank you. Instagram scraping is very challenging, as they dont like it that much :D. Yes all those tools, have different use cases. And they evolve a lot and very fast. Probably I will do a new video soon.
good content!
great video!
Thank you 😊
please, do a tutorial...I need to do the same with Buffet and more knowledge
I can definitely do that, what kind of tutorial you want exactly
@@FlorenzErstling I'm really noob, I don't know how to put all together with CrewAI, I see in github and it's really difficult
Really liked the series but you have the playlist the wrong way around. Currently the results are the first video :D
Thanks a lot, I'm glad you liked it. I ordered the list now correctly, thank you for the hint :)
Your ease of use VS instalation complexity is misleading. The ease of use trait should have it's maximum on the right as that's the established way to present it, yet "easy" is on the left side
True, thank you for pointing it out.
Sure, I should also mention: thank you for this content, it made me install Autogen :)
Where is agency swarm ? If you want fast, use groq, if you want cheap use ollama, if you need something done like this kind of research, speed does not matter, but insightfull results do. So improve prompt and or use better model.
If you cant code, dont use ai frameworks, there zare plenty of other options now, or was opensource a requirement ?
Yes, thats true, of course speed is not a requirement for this task, just wanted to compare the different kpi, then everyon has to choose the framework what fits best for a specific use case.
you should not put your video over the slide contents ;-)
Good point, thanks :)
Thanks for the video but there is something I don’t understand in this « benchmark ». What about the frameworks « output » ?? Does all the frameworks generated exactly the same final report ? I guess not ? Then for a « benchmark » to be meaningful I think it should includes a careful rating of the results. Why would I pick a framework that it slightly faster or easier to install if the produced results are poorer ??
Or did I miss something ??
Many thanks for your thoughts on that…
thats a good point, thank you, the results where actually very similar indeed, but not exactly the same, I will definitely consider it for my next benchmark
Man , your picture have a better place, move it to the bottom left corner, , it is already to much big and cover your content. please shrink ur self 50% and move to the left, or even better hide it , it has no value to the video.
Please stop stomping or maybe hitting with your hand. It is very disturbing.
ok, gonna try :)