TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Agno: Agent framework 10,000x faster than LangChain

47 pointsby bediashpreet3 months ago

11 comments

tomnipotent3 months ago
This &quot;10,000x&quot; faster claim is specific to how long it takes to instantiate a client object, before actually interacting with it.<p>Turns out the LangGraph code uses the official OpenAPI library which eagerly instantiates an HTTPS transport and 65% of runtime was dominated by ssl.create_default_context (SSLContext.load_verify_locations) when I tested using pyinstrument. This overhead is further exasperated by the fact that it&#x27;s happening twice - once for the sync client, and a second time for the async client. Rest of the overhead seems to be Pydantic and setting up the initial state&#x2F;graph.<p>Agno wrote their own OpenAPI wrapper and defers setting up the HTTPS transport during agent creation, so that cost still exists it&#x27;s just not accounted for in this &quot;benchmark&quot;. Agno still seems to be slightly faster when you control for this, but amortized over a couple of requests it&#x27;s not even a rounding error.<p>I hope the developers get rid of this &quot;claim&quot; and focus on other merits.
评论 #43287585 未加载
turnsout3 months ago
Is Python execution even a rounding error in the full execution time for a LangChain flow?
评论 #43292599 未加载
thecleaner3 months ago
Congratulations on the release. Although I hope the developers take the lesson that AI frameworks are unnecessary. You don&#x27;t need frameworks to write HTTP calls. Just a good enough SDK would do.
yuzhun3 months ago
Tried agno. Its API has less mental burden than langchain. As for the speed advantage, it hasn&#x27;t been noticed much.
vivzkestrel3 months ago
how did you arrive at this number 10000?
评论 #43277689 未加载
slake3 months ago
Does it work with o1 type reasoning models. I had trouble running phidata (the old named framework) with it.
eternityforest3 months ago
Can this handle smaller models like Qwen 1.5B, or does it need some real intelligence to get the tool calling to work?
评论 #43286545 未加载
esafak3 months ago
LangGraph, not LangChain.
barbazoo3 months ago
How does this compare to pydantic.ai?
moltar3 months ago
But only in Python.
dcreater3 months ago
Another day another unnecessary ai framework.
评论 #43277527 未加载
评论 #43283041 未加载