Welcome to smolagents on Hugging Face!

smolagents Documentation

Section	Description
🏡 View all docs	Explore all documentation.
AWS Trainium & Inferentia	Learn about AWS integrations.
Amazon SageMaker	Integrate with SageMaker.
Argilla	Argilla integration.
AutoTrain	AutoTrain functionality.
Bitsandbytes	Bitsandbytes support.
Chat UI	Chat UI examples.
Competitions	Participate in competitions.
Dataset viewer	View datasets.
Datasets	Explore datasets.
Diffusers	Diffusers integration.
Distilabel	Distilabel integration.
Evaluate	Model evaluation.
Gradio	Gradio integration.
Hub	Hugging Face Hub.
Hub Python Library	Python Library for the Hub.
Hugging Face Generative AI Services (HUGS)	Generative AI Services.
Huggingface.js	JavaScript library.
Inference Endpoints (dedicated)	Dedicated Inference Endpoints.
Inference Providers	Inference Providers.
Leaderboards	Leaderboards.
Lighteval	Lighteval integration.
Optimum	Optimum integration.
PEFT	PEFT integration.
Safetensors	Safetensors support.
Sentence Transformers	Sentence Transformers.
TRL	TRL integration.
Tasks	Available tasks.
Text Embeddings Inference	Text Embeddings Inference.
Text Generation Inference	Text Generation Inference.
Tokenizers	Tokenizers.
Transformers	Transformers.
Transformers.js	Transformers.js.

Search Documentation

Versions

v1.13.0 | v1.12.0 | v1.11.0 | v1.10.0 | v1.9.2 | v1.8.1 | v1.7.0 | v1.6.0 | v1.5.1 | v1.4.1 | v1.3.0 | v1.2.2 | v1.1.0 | v0.1.3

Get started

🤗 Agents

Guided tour

Tutorials

Building good agents

📊 Inspect your agent runs using telemetry

🛠️ Tools - in-depth guide

🛡️ Secure code execution

📚 Manage your agent's memory

Conceptual guides

🤖 An introduction to agentic systems

🤔 How do Multi-step agents work?

Examples

Self-correcting Text-to-SQL

Master you knowledge base with agentic RAG

Orchestrate a multi-agent system

Build a web browser agent using vision models

Reference

Agent-related objects

Model-related objects

Tool-related objects

Join the Hugging Face community

and get access to the augmented documentation experience

Collaborate on models, datasets and Spaces

Faster examples with accelerated inference

Switch between documentation themes

Sign Up to get started

What are Agents?

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 theirtransformersversion or through our inference API and Inference providers, 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 Gradio Spaces as tools to/from the Hub, and more is to come!

Guided tour

Learn the basics and become familiar with using Agents. Start here if you are using Agents for the first time!

How-to guides

Practical guides to help you achieve a specific goal: create an agent to generate and test SQL queries!

Conceptual guides

High-level explanations for building a better understanding of important topics.

Tutorials

Horizontal tutorials that cover important aspects of building agents.

Guided tour