Hi, everyone!
Especially, my friends @seand0101 and @John6666 !
I know new framework emerged in the huggingface. I think that is very helpful to create the agent for using LLMs. We used langchain or langgraph to combinate the toolkits and LLMs, but there is some problems cause the code is too long and complicated. Then new framework emerged, it is clear.
Let’s talk about smolagents. I will give you some small information about smolagents.
Then if you have experienced to use this framework, please share the code and explanation for helping others.
This library is the simplest framework out there to build powerful agents! By the way, wtf are “agents”? We provide our definition in this page, where you’ll also find tips for when to use them or not (spoilers: you’ll often be better off without agents).
This library offers:
Simplicity: the logic for agents fits in ~thousand lines of code. We kept abstractions to their minimal shape above raw code!
Support for any LLM: it supports models hosted on the Hub loaded in their transformers version or through our inference API, but also models from OpenAI, Anthropic… it’s really easy to power an agent with any LLM.
First-class support for Code Agents, i.e. agents that write their actions in code (as opposed to “agents being used to write code”), read more here.
Hub integrations: you can share and load tools to/from the Hub, and more is to come!
There’s even a dedicated channel on Discord.