🚀 Big news for TRL users with AI agents: We just released the trl-training SKILL in TRL v0.29.0 🤗 Agents can now use the TRL CLI as a structured capability:

5 years already working in democratizing AI 🤗 Grateful to be part of such an awesome team making it happen every day.

Latest smolagents release supports GPT-5: build agents that think, plan, and act. ⚡ Upgrade now and put GPT-5 to work!

🚀 smolagents v1.21.0 is here! Now with improved safety in the local Python executor: dunder calls are blocked! ⚠️ Still, not fully isolated: for untrusted code, use a remote executor instead: Docker, E2B, Wasm. ✨ Many bug fixes: more reliable code. 👉 github.com/huggingface/...

Release v1.21.0 · huggingface/smolagents

Enhancements ✨ Tool & Model Improvements Add Tool to_code_prompt and to_tool_calling_prompt by @albertvillanova in #1599 Improve function body extraction in tools by @HairlessVillager in #1627 S...

github.com

💥 Big milestone just dropped in smolagents: The CodeAgent can now execute Python code remotely in WebAssembly, powered by Pyodide + Deno! Your agent-generated Python runs in a secure, sandboxed Wasm runtime: no local execution required. Here's why this changes the game 🧵👇

🚀New Release: smolagents v1.19.0 is out! This one's packed with agent upgrades, smoother streaming, better docs, and bug squashing galore. 🧵👇

New in smolagents v1.17.0: - Structured generation in CodeAgent 🧱 - Streamable HTTP MCP support 🌐 - Agent.run() returns rich RunResult 📦 Smarter agents, smoother workflows. Try it now: github.com/huggingface/...

Release v1.17.0 · huggingface/smolagents

New Features ✨ Structured Generation in CodeAgent: Add optional support for structured outputs in CodeAgent, enabling more reliable and consistent generation patterns Adding optional structured g...

github.com

🚀 Experiment with Tiny Agents: minimalist LLM agents powered by async MCP tools, inspired by @julien_c 🔍 A side-by-side comparison of tool-calling vs. code agent 💡 See how code agents handle complex workflows in one step, reducing model calls and boosting efficiency!

TinyAgents: A Minimal Experiment with Code Agents and MCP Tools

A Blog post by Albert Villanova del Moral on Hugging Face

huggingface.co

New in smolagents v1.16.0: 🔍 Bing support in WebSearchTool 🐍 Custom functions & executor_kwargs in LocalPythonExecutor 🔧 Streaming GradioUI fixes 🌐 Local web agents via api_base & api_key 📚 Better docs 👉 github.com/huggingface/smolagents

Code Agents generate full code blocks and execute them in one go, instead of calling tools one-by-one. Learn how to build smarter, faster agents in a new @deeplearningai.bsky.social course by @hf.co. Build with smolagents → sandboxed, reliable, powerful. 🔗 www.deeplearning.ai/short-course...

Building Code Agents with Hugging Face smolagents

Build agents that write and execute code to perform complex tasks, using Hugging Face’s smolagents.

deeplearning.ai

smolagents v1.14.0 is out! 🚀 🔌 MCPClient: A sleek new client for connecting to remote MCP servers, making integrations more flexible and scalable. 🪨 Amazon Bedrock: Native support for Bedrock-hosted models. SmolAgents is now more powerful, flexible, and enterprise-ready. 💼

Release v1.14.0 · huggingface/smolagents

New features 🚀 SmolAgents MCP Client by @grll in #1200 Introduce a new MCPClient class that allows users to manage connections to one or more MCP servers, making integration with SmolAgents more ...

github.com

Imagine a gender equal world. A world free of bias, stereotypes, and discrimination. A world that's diverse, equitable, and inclusive. A world where difference is valued and celebrated. Together we can forge gender equality. Collectively for #IWD2025 we can all #AccelerateAction

International Women's Day 2025 campaign theme: Accelerate Action

FREE International Women's Day 2025 theme resources - #IWD2025

internationalwomensday.com

🚀 New smolagents update: Safer Local Python Execution! 🦾🐍 With the latest release, we've added security checks to the local Python interpreter: every evaluation is now analyzed for dangerous builtins, modules, and functions. 🔒 Here's why this matters & what you need to know! 🧵👇

🚀 Big news for AI agents! With the latest release of smolagents, you can now securely execute Python code in sandboxed Docker or E2B environments. 🦾🔒 Here's why this is a game-changer for agent-based systems: 🧵👇

🚀 Introducing @hf.co 🤗 Open Deep-Research💥 In just 24 hours, we built an open-source agent that: ✅ Autonomously browse the web ✅ Search, scroll & extract info ✅ Download & manipulate files ✅ Run calculations on data 55% on GAIA validation set! Help us improve it!💡 huggingface.co/blog/open-de...

Open-source DeepResearch – Freeing our search agents

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

huggingface.co

Discover all the improvements in the new version of Lighteval: huggingface.co/docs/lightev...

Lighteval

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

huggingface.co

🚀 The Open LLM Leaderboard just got a glow-up! 🌟 ⚡ Faster, 🪶 lighter, 🧠 more intuitive: everything you need, now easier to explore. Dive into the sleek new frontend: huggingface.co/spaces/open-...

Check out how easy it is to do LLM evals with LightEval! * any dataset on the 🤗 Hub can become an eval task in a few lines of code: customize the prompt, metrics, parsing, few-shots, everything! * model- and data-parallel inference * auto batching with the new vLLM backend

🚨 How green is your model? 🌱 Introducing a new feature in the Comparator tool: Environmental Impact for responsible #LLM research! 👉 huggingface.co/spaces/open-... Now, you can not only compare models by performance, but also by their environmental footprint!

Open LLM Leaderboard Model Comparator - a Hugging Face Space by open-llm-leaderboard

Compare Open LLM Leaderboard results

huggingface.co