Cette page est affichée en anglais. Une traduction française est en cours.
ScriptsMar 29, 2026·1 min de lecture

Smolagents — Lightweight AI Agent Framework

Hugging Face minimalist agent framework. Build AI agents in ~1000 lines of code with code-based actions, tool calling, and multi-step reasoning.

Introduction

Smolagents is Hugging Face's lightweight agent framework — the core library is ~1000 lines of code. Agents write and execute Python code as their actions, making them more flexible and debuggable than JSON-based tool calling.

Best for: Quick agent prototyping, research, code-executing agents Works with: OpenAI, Anthropic, HuggingFace models, local models


Key Concept: Code Agents

Instead of outputting JSON tool calls, smolagents agents write Python code:

from smolagents import CodeAgent, tool, HfApiModel

@tool
def get_weather(city: str) -> str:
    """Get current weather for a city."""
    return f"Sunny, 22C in {city}"

agent = CodeAgent(tools=[get_weather], model=HfApiModel())
agent.run("What's the weather in Tokyo?")

The agent writes: result = get_weather("Tokyo") and executes it.


Why Code Agents?

  • More expressive — loops, conditionals, variables
  • Composable — chain tool calls naturally
  • Debuggable — read the generated code
  • Efficient — fewer LLM calls than ReAct

FAQ

Q: What is Smolagents? A: Hugging Face minimalist agent framework. Build AI agents in ~1000 lines of code with code-based actions, tool calling, and multi-step reasoning.

Q: How do I install Smolagents? A: Check the Quick Use section above for step-by-step installation instructions. Most assets can be set up in under 2 minutes.

🙏

Source et remerciements

Created by Hugging Face. Licensed under Apache 2.0. huggingface/smolagents

Discussion

Connectez-vous pour rejoindre la discussion.
Aucun commentaire pour l'instant. Soyez le premier à partager votre avis.

Actifs similaires