Agentic WeeklyGet the weekly
Hugging Facev1.26.0Tested (smoke test)

smolagents: what’s new in v1.26.0 and our verdict

Hugging Face's small Python library for agents that write and run code; the docs say the core logic fits in roughly a thousand lines.

Official site

Release Ruler for smolagents: marked at its Tested release date on the timeline of every AI model we track.

At a glance

Evidence
Tested (smoke test)
Released
May 29, 2026
Last verified
Oct 25, 2026
Pricing
Official page, dated
Best for
agent building

Evidence and ranking

Evidence behind this verdict

  1. Sources read2 cited sources, latest fetched Oct 25, 2026. (done)
  2. Facts re-checkedLast verified Oct 25, 2026. (done)
  3. Run by usSmoke test on Oct 25, 2026 (scope below). (done)

Passed Test log result: Passed. Read the log

Where we rank it (editorial)

Listed here but not yet ranked. Ranks are editorial picks, not benchmark scores.

Pricing: Open-source library; costs come from the model APIs you call. (checked 2026-10-25)

Our verdict

Hugging Face's small Python library for agents that write and run code; the docs say the core logic fits in roughly a thousand lines.

Good for

  • People who want a small hackable agent library
  • Code-as-action agent experiments

Skip if

  • You need a full production orchestration platform

Tested. Tested 2026-10-25 (America/Chicago). smolagents 1.26.0 passed our one-tool task on a local 3B model: 6 of 6 trials; cold uv install 1.5 s. Test environment: Linux x86_64 virtual machine (Debian 13), 8 vCPU, 15 GiB RAM, no GPU; no vendor account, login or API key. Agent tools were pointed at a local open-weight model (Qwen2.5-3B-Instruct (Q4_K_M) through Ollama 0.40.11), so we tested the tool, not any vendor's hosted models. Not tested: Any vendor-hosted model: everything ran on a local 3B model, so tool-call reliability with frontier models is not measured here; Multi-agent flows, memory, long conversations, streaming, tracing and cloud deployment; Anything beyond one tool and one question; three trials is a smoke test, not a benchmark; The CodeAgent sandboxes (Docker, E2B, Modal) and the hub tools. These are smoke tests, not a benchmark. Full log: /tests/smolagents.

Full test log with exact commands, versions and raw output: smolagents 1.26.0: our test log.

Evidence
Tested (smoke test, 2026-10-25, local 3B model (Qwen2.5-3B)). A smoke test is not a benchmark.
What we ran
smolagents 1.26.0 passed our one-tool task on a local 3B model: 6 of 6 trials; cold uv install 1.5 s.
Model used
Qwen2.5-3B-Instruct (Q4_K_M) through Ollama 0.40.11
Environment
Linux x86_64 virtual machine (Debian 13), 8 vCPU, 15 GiB RAM, no GPU; no vendor account, login or API key
Not tested
Any vendor-hosted model: everything ran on a local 3B model, so tool-call reliability with frontier models is not measured here; Multi-agent flows, memory, long conversations, streaming, tracing and cloud deployment; Anything beyond one tool and one question; three trials is a smoke test, not a benchmark; The CodeAgent sandboxes (Docker, E2B, Modal) and the hub tools.
Date
(America/Chicago)

Best for

Key facts

The smolagents docs describe an open-source Python library for building and running agents in a few lines of code, with abstractions kept minimal. The repository is Apache-2.0 and the latest release we saw is v1.26.0 on May 29, 2026.

  • License: Apache-2.0 (per GitHub)
  • Platforms: Python
  • Pricing model: Free and open source
  • Free tier: Free to self-host
  • Paid plans: None listed for the library
  • GitHub: huggingface/smolagents: 30,051 stars on 2026-10-25, last push 2026-10-22
  • Latest release we saw: v1.26.0, 2026-05-29
  • How to start: pip install smolagents and follow the docs' first agent example.
  • v1.26.0 (2026-05-29): the newest release listed on the official page or repository when we read it on 2026-10-25.

How to set it up: Get started with smolagents

These steps come from the vendor's own pages as read on 2026-10-25. We ran smolagents on 2026-10-25; the test log lists what was and was not covered.

  1. Get access

    pip install smolagents and follow the docs' first agent example.

  2. Check the limits and costs first

    Free to self-host. Open-source library; costs come from the model APIs you call.

Pros and cons

Pros

  • Small codebase
  • Apache-2.0

Cons

  • Last release tag we saw is from May 2026
  • Our test was one small task on a local 3B model; it does not show behaviour with hosted models or larger jobs

Alternatives and comparisons

  • Pydantic AI: Python agent framework built on Pydantic types, covering agents, realtime voice, image generation and embeddings.
  • LangChain: Open-source framework for building LLM applications and agents in Python and JavaScript, from the team behind LangGraph and LangSmith.
  • CrewAI: Python framework for orchestrating role-playing, autonomous AI agents that work as a crew.
  • Langflow: MIT-licensed visual builder for AI agents and MCP servers with a very large GitHub following.

FAQ

What is smolagents?

The smolagents docs describe an open-source Python library for building and running agents in a few lines of code, with abstractions kept minimal. The repository is Apache-2.0 and the latest release we saw is v1.26.0 on May 29, 2026.

Is smolagents free?

Free to self-host. Open-source library; costs come from the model APIs you call. Checked 2026-10-25; prices change, so confirm on the vendor's page.

What license is smolagents under?

Its license: Apache-2.0 (per GitHub). Read from the project's own pages on 2026-10-25.

Sources

Last verified · Agentic Weekly

  • Langflow: MIT-licensed visual builder for AI agents and MCP servers with a very large GitHub following.
  • Botpress: Customer-support AI agent platform with a free plan and conversation-based paid plans.
  • Gumloop: Agent builder for teams; plans start at $37 per month with 20k included credits.

How to cite this page

Agentic Weekly, "smolagents v1.26.0: what's new, verdict & setup", last updated 2026-10-25, https://theagenticweekly.com/tools/smolagents

Keep the Reported or Tested label when you quote a verdict. Plain-text version: https://theagenticweekly.com/tools/smolagents.md. More for AI assistants: /ai, /tools.json, /llms.txt.