smolagents
Project record
Maintained by Hugging Face13
smolagents is an open-source Python library from Hugging Face for building agents with few abstractions. Its CodeAgent writes its actions as Python code, a ToolCallingAgent uses conventional tool calling, and agents and tools can be shared through the Hugging Face Hub.13
- Repository: Repository (external site: github.com)
- Documentation: Documentation (external site: huggingface.co)
- License: LICENSE (external site: github.com)
- Release notes: Reviewed release (external site: github.com)
Availability and license
Overall availability
Source code is public and the package installs from PyPI. Hosted model providers require their own accounts or API keys; local models run through Transformers or Ollama.143
Availability is separate from permission: read the license before using or redistributing.
Component reuse rights
- weights
- Unknown — no complete fact-level rights review
- code
- Reviewed qualifying license recorded — check scope and conditions
- data
- Unknown — no complete fact-level rights review
- documentation
- Unknown — no complete fact-level rights review
No complete system-rights review is recorded for this release.
Public materials checklist
| Item | Status | Notes and evidence |
|---|---|---|
| Source codeIs the source code publicly readable? | Public | Public repository; library code only.1 |
| DocumentationIs user documentation published? | Public | Public official documentation on the Hugging Face documentation site.34 |
| InstallationAre installation instructions or packages publicly available? | Public | Installed with pip or uv; optional extras add tools (toolkit, mcp), model integrations (openai, transformers, vllm, mlx-lm, litellm, bedrock), remote execution (blaxel, e2b, docker), and telemetry or Gradio UI support.4 |
| Supported platformsAre supported operating systems or hardware documented? | Public | The installation guide requires Python 3.10 or newer with pip or uv; it does not list operating-system restrictions.4 |
| Release statusAre versioned releases published? | Public | Reviewed v1.26.0, the latest release at review, published May 29, 2026; commits to the main branch continued through September 30, 2026. This entry describes the project rather than one release.56 |
What it is useful for
Building code-executing or tool-calling agents with models from many sources. The library is client code and does not include model weights; it can run models locally through Transformers or Ollama, or call hosted models through Hugging Face Inference Providers, LiteLLM, or OpenAI-compatible servers, whose terms and openness vary by model and provider.13
Run and use notes
- The documentation describes running models locally with Transformers (the transformers extra) or Ollama and lists vllm and mlx-lm extras. The README warns that the built-in LocalPythonExecutor is not a security boundary and recommends running agent code in a sandbox such as E2B, Blaxel, Modal, or Docker.341
Organization context
U.S. eligibility
Eligible · basis: U.S.-governed project
smolagents is developed in Hugging Face's GitHub organization, its README carries a copyright notice for the HuggingFace Team, and its documentation is published on Hugging Face's documentation site. Hugging Face's terms of service identify Hugging Face, Inc., a Delaware corporation, as the provider of its services under New York law, and its privacy policy states that the company and its servers are located in the United States (a French entity is named as its EU main establishment). NVIDIA announced on September 3, 2026 an agreement to acquire Hugging Face; this assessment does not rely on it. See the hugging-face organization record for the full dual-country assessment.13789
Sources
This listing is not an endorsement, a safety assessment, or a federal approval.