---
title: "smolagents Code-First AI Agent Library"
description: "smolagents is HuggingFace's barebones Python library for building AI agents that think in code rather than JSON. Agents write and execute Python code as their action space, enabling more flexible reasoning and tool use with support for sandboxed execution via E2B, Docker, or WebAssembly."
verification: "security_reviewed"
source: "https://github.com/huggingface/smolagents"
category:
  - "Developer Tools"
framework:
  - "Custom Agents"
tool_ecosystem:
  github_repo: "huggingface/smolagents"
  github_stars: 26355
---

# smolagents Code-First AI Agent Library

smolagents is HuggingFace's barebones Python library for building AI agents that think in code rather than JSON. Agents write and execute Python code as their action space, enabling more flexible reasoning and tool use with support for sandboxed execution via E2B, Docker, or WebAssembly.

## Installation

Choose whichever fits your setup:

1. Copy this skill folder into your local skills directory.
2. Clone the repo and symlink or copy the skill into your agent workspace.
3. Add the repo as a git submodule if you manage shared skills centrally.
4. Install it through your internal provisioning or packaging workflow.
5. Download the folder directly from GitHub and place it in your skills collection.

## Source

- [Agent Skill Exchange](https://agentskillexchange.com/skills/smolagents-code-first-ai-agent-library/)