Introducing smolagents, a simple library to build agents (Huggingface)

Jan 5 (edited) • 💬 General

"""

Introducing smolagents: making agents simple 🥳

We built smolagents with these objectives:

✨ Simplicity: the logic for agents fits in ~thousand lines of code (see this file). We kept abstractions to their minimal shape above raw code!

🧑‍💻 First-class support for Code Agents, i.e. agents that write their actions in code (as opposed to "agents being used to write code"). To make it secure, we support executing in sandboxed environments via E2B.

On top of this CodeAgent class, we still support the standard ToolCallingAgent that writes actions as JSON/text blobs.

🤗 Hub integrations: you can share and load tools to/from the Hub, and more is to come!

🌐 Support for any LLM: it supports models hosted on the Hub loaded in their transformers version or through our inference API, but also supports models from OpenAI, Anthropic and many others via our LiteLLM integration.

smolagents is the successor to transformers.agents, and will be replacing it as transformers.agents gets deprecated in the future.

"""

It simplifies access to coding tools through the use of Python libraries as LLM tools, as well as the more standard LLM too calling agent via JSON/Text.

0 comments