smolagents

smolagents is an open-source Python library developed by Hugging Face that enables developers to build and run powerful AI agents with minimal code. The library provides two primary agent paradigms: CodeAgent, which writes actions as Python code snippets for maximum expressiveness and composability, and ToolCallingAgent, which uses structured JSON for reliable and safe tool interactions. smolagents is model-agnostic, supporting Hugging Face Inference Providers, local Transformers, Ollama, LiteLLM (100+ LLMs), Azure OpenAI, Amazon Bedrock, and MLX models. Hub integration allows teams to share and load agents and tools as Gradio Spaces, and multi-agent orchestration enables hierarchical systems where manager agents coordinate specialized sub-agents.

smolagents publishes 1 API on the APIs.io network. Tagged areas include AI Agents, Multi-Agent, Python, Code Generation, and LLM.

The smolagents catalog on APIs.io includes 1 JSON-LD context.

smolagents’ developer surface includes documentation, engineering blog, changelog, pricing, and 16 more developer resources.

🌐 Visit website 📡 Source on GitHub

28.4/100 thin ▬ flat Agent 3/100 human only Full breakdown ↓
scored 2026-08-25 · rubric v0.14.0

AccessFreemium

1 APIs

AI Agents Multi-Agent Python Code Generation LLM Hugging Face Open-Source Machine-Learning

Kin Score

Kin Score How this is scored →
scored 2026-08-25 · rubric v0.14.0

Composite quality — 28.4/100 · thin

Contract Quality 2.7 / 25

Developer Ergonomics 2.4 / 20

Access Clarity 10.0 / 20

Operational Transparency 6.5 / 13

Contract Governance 0.0 / 12

Discoverability 6.9 / 10

Agent readiness — 3/100 · human only

Machine-Readable Contract 0 / 18

Agentic Access Contract 0 / 10

Documented Reversibility 0 / 6

MCP Server 0 / 12

Machine-Readable Auth 0 / 10

Idempotency 0 / 9

Stable Error Semantics 0 / 8

Request/Response Examples 0 / 7

Rate-Limit Signaling 7 / 7

Typed Event Surface 0 / 6

Agent Skills 0 / 5

Well-Known Catalog 0 / 4

Consent & Bot Identity 0 / 3

A2A Agent Card 0 / 8

Dry-Run / Simulate Mode 0 / 4

Delegated User Identity 0 / 6

Protected Resource Metadata 0 / 5

Registration Without a Human 0 / 6

Agentic Commerce Surface 0 / 5

Improve this rating by publishing the missing artifacts — every area above can be raised, and the full rubric is at apis.io/rating/. This rating is computed from github.com/api-evangelist/smolagents: open an issue to ask a question, or submit a pull request to add artifacts. Want it done for you? Prioritized profiling — $2,500 →

APIs 1

Individual APIs this provider publishes, each with its own machine-readable definition.

Rate Limits 1

Documented rate limits and quota policies.

Smolagents Rate Limits

21 limits

RATE LIMITS

FinOps 1

Cost, billing, and metering signals for API financial operations.

Documentation 1

Reference material describing how the API behaves

Documentation

Documentation

Design & Contract 1

Pagination, idempotency, versioning, errors, and events

JSONLDContext

JSONLDContext

Build 2

SDKs, sample code, and the tooling you integrate with

GitHubOrganization

GitHubOrganization

GitHubRepository

GitHubRepository

Access & Security 2

Authentication, authorization, and security posture

VulnerabilityDisclosure

VulnerabilityDisclosure

DomainSecurity

DomainSecurity

Operate 3

Status, limits, changes, and where to get help

ChangeLog

ChangeLog

StatusPage

StatusPage

RateLimits

RateLimits

Commercial 4

Pricing, plans, and the legal terms of use

License

Pricing

Plans

FinOps

Company 5

The organization behind the API

Website

Website

Blog

Blog

LinkedIn

BlogRSS

BlogRSS

Blog

Blog

Other 2

Properties that don't map to a standard resource type

PyPI

PyPI

Source (apis.yml)

aid: smolagents
name: smolagents
description: 'smolagents is an open-source Python library developed by Hugging Face that enables developers to build and run
  powerful AI agents with minimal code. The library provides two primary agent paradigms: CodeAgent, which writes actions
  as Python code snippets for maximum expressiveness and composability, and ToolCallingAgent, which uses structured JSON for
  reliable and safe tool interactions. smolagents is model-agnostic, supporting Hugging Face Inference Providers, local Transformers,
  Ollama, LiteLLM (100+ LLMs), Azure OpenAI, Amazon Bedrock, and MLX models. Hub integration allows teams to share and load
  agents and tools as Gradio Spaces, and multi-agent orchestration enables hierarchical systems where manager agents coordinate
  specialized sub-agents.

  '
type: Index
accessModel:
  pricing: freemium
  onboarding: unknown
  trial: false
  try_now: false
  public: false
  label: Freemium
  confidence: medium
  source:
  - plans
  generated: '2026-07-22'
  method: derived
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/icons/smolagents.png
tags:
- AI Agents
- Multi-Agent
- Python
- Code Generation
- LLM
- Hugging Face
- Open-Source
- Machine-Learning
tags_raw:
- AI Agents
- Multi-Agent
- Python
- Code Generation
- LLM
- Hugging Face
- Open Source
- Machine Learning
url: https://raw.githubusercontent.com/api-evangelist/smolagents/refs/heads/main/apis.yml
created: '2026-06-12'
modified: '2026-06-12'
specificationVersion: '0.23'
apis:
- aid: smolagents:smolagents-python-library
  name: smolagents Python Library
  description: 'The core smolagents Python library providing CodeAgent and ToolCallingAgent classes for building AI agents
    that write Python code or structured JSON to call tools and orchestrate multi-agent systems. Integrates with Hugging Face
    Hub Inference Providers, LiteLLM, Transformers, Azure OpenAI, Amazon Bedrock, and local models via Ollama.

    '
  humanURL: https://huggingface.co/docs/smolagents/en/index
  baseURL: https://huggingface.co
  tags:
  - Agents
  - Python
  - Code Agents
  - Tool Calling
  - Multi-Agent
  properties:
  - type: Documentation
    url: https://huggingface.co/docs/smolagents/en/index
  - type: GuidedTour
    url: https://huggingface.co/docs/smolagents/en/guided_tour
  - type: APIReference
    url: https://huggingface.co/docs/smolagents/reference/agents
  - type: PyPI
    url: https://pypi.org/project/smolagents/
  - type: GitHubRepository
    url: https://github.com/huggingface/smolagents
common:
- type: License
  name: Apache-2.0
  url: https://github.com/huggingface/smolagents/blob/main/LICENSE
- type: VulnerabilityDisclosure
  url: security/smolagents-vulnerability-disclosure.yml
- type: DomainSecurity
  url: security/smolagents-domain-security.yml
- type: Website
  url: https://huggingface.co/smolagents
- type: Documentation
  url: https://huggingface.co/docs/smolagents/en/index
- type: GitHubOrganization
  url: https://github.com/huggingface
- type: GitHubRepository
  url: https://github.com/huggingface/smolagents
- type: Blog
  url: https://huggingface.co/blog/smolagents
- type: ChangeLog
  url: https://github.com/huggingface/smolagents/releases
- type: PyPI
  url: https://pypi.org/project/smolagents/
- type: Pricing
  url: https://huggingface.co/pricing
- type: StatusPage
  url: https://status.huggingface.co
- type: X
  url: https://x.com/huggingface
- type: LinkedIn
  url: https://www.linkedin.com/company/huggingface
- type: Plans
  url: https://raw.githubusercontent.com/api-evangelist/smolagents/refs/heads/main/plans/smolagents-plans-pricing.yml
- type: RateLimits
  url: https://raw.githubusercontent.com/api-evangelist/smolagents/refs/heads/main/rate-limits/smolagents-rate-limits.yml
- type: FinOps
  url: https://raw.githubusercontent.com/api-evangelist/smolagents/refs/heads/main/finops/smolagents-finops.yml
- type: BlogRSS
  url: https://huggingface.co/blog/feed.xml
- type: Blog
  url: https://raw.githubusercontent.com/api-evangelist/smolagents/refs/heads/main/blogs/blogs.json
- type: JSONLDContext
  url: https://raw.githubusercontent.com/api-evangelist/smolagents/refs/heads/main/json-ld/smolagents-context.jsonld
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com

Work with this as data

Every provider here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for providers

9 MCP tools reach this

find_providersBrowse and filter every provider in the catalog.
get_provider_artifactsEvery artifact this provider publishes, grouped by type.
get_provider_operationsEvery operation across all of their OpenAPIs — one call instead of parsing every spec.
get_provider_toolsEvery MCP tool they ship, with the operation each wraps.
get_provider_evidenceHow each part of their score was established. Free — the basis for a claim should not sit behind it.
get_provider_ratingPRO — composite, band, trend and facet scores.
apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
resolveTurn a domain, URL or GitHub org into the provider it belongs to.
find_cohortsEvery scored population of providers in the catalog.

All 92 tools

Call it yourself

curl for this page

This provider

curl "https://apis.io/api/v1/providers/smolagents"

All providers

curl "https://apis.io/api/v1/providers?limit=25"

Every operation they expose

curl "https://apis.io/api/v1/providers/smolagents/operations?limit=25"

How their score was established

curl "https://apis.io/api/v1/providers/smolagents/evidence"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no email required.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have.

smolagents

Kin Score

APIs 1

smolagents Python Library

Pricing Plans 1

Smolagents Plans Pricing