huggingface/smolagents
🤗 smolagents: a barebones library for agents that think in code. observed · 2026-10-17
Health v2 · maintenance only
81/100
- Activity 98
- Release rhythm 78
- Longevity 48
How is this computed?
round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-10-21. Adoption (stars, forks) is never an input.
- gap_med: 8
- age_days: 684
- days_rel: 144
- days_push: 14
- n_releases_24m: 36
Adoption not part of the score
29890 stars · 3093 forks observed · 2026-10-17
What it is AI-extracted, prompt v1, taxonomy v1, 2026-10-05, confidence 0.98
smolagents is a lightweight Python library for building and running LLM‑powered agents with just a few lines of code. It provides first‑class support for CodeAgents that generate Python code for tool calls and can execute them securely in sandboxed environments.
Use cases
- create an autonomous chatbot that can browse the web and answer user questions
- automate data‑pipeline steps by letting an LLM orchestrate tool calls
- build a research assistant that can run code snippets and retrieve results
- integrate custom tools from the Hugging Face Hub into an LLM workflow
- debug and monitor multi‑step agent runs with OpenTelemetry
When to choose
- you need a simple, minimal‑dependency library to prototype LLM agents
- your agent logic benefits from writing actions as Python code rather than JSON
- you want built‑in support for secure sandboxed execution (Docker, Modal, etc.)
- you plan to share or reuse tools via the Hugging Face Hub
When to avoid
- you require a full‑featured orchestration platform with distributed scheduling
- your project depends on a specific agent framework not supported by smolagents
- you need native support for non‑Python runtimes without extra wrappers
Facets
library · maturity active
api-framework artificial-intelligence python cloud code-agent tool-calling-agent huggingface-hub secure-execution open-telemetry tool-calling sandboxing agent-framework docker
10 sources
- readme: https://github.com/huggingface/smolagents · fetched 2026-10-17 · 6fd08c57e5ea
- homepage: https://huggingface.co/docs/smolagents · fetched 2026-09-21 · 2b30560b672d
- site_page: https://huggingface.co/docs/smolagents/tutorials/building_good_agents · fetched 2026-09-21 · ce46878a0f5d
- site_page: https://huggingface.co/docs/smolagents/tutorials/inspect_runs · fetched 2026-09-21 · 42f6f7f7e22d
- site_page: https://huggingface.co/docs/smolagents/tutorials/tools · fetched 2026-09-21 · 856048a0ced8
- site_page: https://huggingface.co/docs/smolagents/tutorials/secure_code_execution · fetched 2026-09-21 · fbb2a72d4753
- site_page: https://huggingface.co/docs · fetched 2026-09-21 · bdec26667b98
- site_page: https://huggingface.co/docs/smolagents/installation · fetched 2026-09-21 · 206a3c8ed60c
- site_page: https://huggingface.co/docs/smolagents/guided_tour · fetched 2026-09-21 · ee07d8c229f8
- site_page: https://huggingface.co/pricing · fetched 2026-09-21 · de6b7a178be5
Member repositories
| Repository | Role | Health v2 |
|---|---|---|
| huggingface/smolagents | main | 81 |
For agents
markdown · JSON · MCP: product_card(name="huggingface/smolagents")
Data as of 2026-10-19T08:05:51.212177+00:00 · Report a problem