SmolAgents

Profile

Overview

The bottom line — what this framework is, who it's for, and when to walk away.

Bottom Line Up Front

SmolAgents is an open-source Python library designed to easily build and run agents with minimal code. It supports both code-execution and tool-calling agents, is model and tool-agnostic, and integrates with Hugging Face Hub. Secure code execution and modality-agnostic capabilities extend its utility.

Best For

Rapidly building, running, and sharing LLM agents, especially those executing Python code securely.

Avoid If

Executing untrusted `CodeAgent` prompts without configuring a sandboxed environment.

Strengths

  • +Provides a simple API for agent development, with agent logic fitting in approximately 1000 lines of code.
  • +Offers first-class support for `CodeAgent`s that write and execute Python code, enabling natural composability.
  • +Supports secure code execution in sandboxed environments via Modal, Blaxel, E2B, or Docker.
  • +Includes `ToolCallingAgent` support for traditional JSON/text-based tool invocation paradigms.
  • +Integrates seamlessly with Hugging Face Hub for sharing and loading agents and tools as Gradio Spaces.
  • +Is model-agnostic, supporting Hugging Face Inference providers, OpenAI, Anthropic (via LiteLLM), and local models (Transformers, Ollama).
  • +Is modality-agnostic, capable of handling vision, video, and audio inputs for broader application types.
  • +Is tool-agnostic, allowing integration with tools from MCP servers, LangChain, or other Hugging Face Spaces.
  • +Includes command-line utilities (smolagent, webagent) for quick agent execution without boilerplate code.

Weaknesses

  • Potential security risks exist if `CodeAgent` is used to execute untrusted code without configuring a sandboxed environment.
  • Minimalistic abstractions may require more direct coding or boilerplate for highly customized or complex agent workflows.
  • No explicit mention of built-in memory management or long-term conversational state management is provided.

Project Health

Is this project alive, well-maintained, and safe to bet on long-term?

Stars

28,067

Open Issues

639

Last Commit

12d ago

Commit Frequency

<1x/week

Bus Factor Score

9 / 10

Maintainers

100

Latest Version

v1.26.0

Total Releases

36

Repo Age

1y 6mo

Forks

2,716

Monthly Downloads

654K

last 30 days

Versions Published

42

Known Vulnerabilities

5Highest: Critical

Dependent Repos

0

public repos using this

Fit

Does it support the workflows, patterns, and capabilities your team actually needs?

State Management

no data

Perspective

Your expertise shapes what we build next.

We build for engineers who make real architectural decisions. If something is missing, inaccurate, or could be more useful — we want to hear it.

Last updated: 29 June 2026

·

FrameworkPicker — The technical decision engine for the agentic AI era.