Post
4367
Latest smolagents release supports GPT-5: build agents that think, plan, and act.
β‘ Upgrade now and put GPT-5 to work!
β‘ Upgrade now and put GPT-5 to work!
- 1 reply
AI & ML interests
None defined yet.
albertvillanovaΒ
posted
an
update
5 months ago
albertvillanovaΒ
posted
an
update
5 months ago
Post
668
π smolagents v1.21.0 is here!
Now with improved safety in the local Python executor: dunder calls are blocked!
β οΈ Still, not fully isolated: for untrusted code, use a remote executor instead: Docker, E2B, Wasm.
β¨ Many bug fixes: more reliable code.
π https://github.com/huggingface/smolagents/releases/tag/v1.21.0
Now with improved safety in the local Python executor: dunder calls are blocked!
β οΈ Still, not fully isolated: for untrusted code, use a remote executor instead: Docker, E2B, Wasm.
β¨ Many bug fixes: more reliable code.
π https://github.com/huggingface/smolagents/releases/tag/v1.21.0
lhoestqΒ
updated
a
dataset
6 months ago
Can't load the dataset after datasets v4.0 release
3
#17 opened 6 months ago
by
nikita-savelyev-intel
albertvillanovaΒ
posted
an
update
6 months ago
Post
792
π New in smolagents v1.20.0: Remote Python Execution via WebAssembly (Wasm)
We've just merged a major new capability into the smolagents framework: the CodeAgent can now execute Python code remotely in a secure, sandboxed WebAssembly environment!
π§ Powered by Pyodide and Deno, this new WasmExecutor lets your agent-generated Python code run safely: without relying on Docker or local execution.
Why this matters:
β Isolated execution = no host access
β No need for Python on the user's machine
β Safer evaluation of arbitrary code
β Compatible with serverless / edge agent workloads
β Ideal for constrained or untrusted environments
This is just the beginning: a focused initial implementation with known limitations. A solid MVP designed for secure, sandboxed use cases. π‘
π‘ We're inviting the open-source community to help evolve this executor:
β’ Tackle more advanced Python features
β’ Expand compatibility
β’ Add test coverage
β’ Shape the next-gen secure agent runtime
π Check out the PR: https://github.com/huggingface/smolagents/pull/1261
Let's reimagine what agent-driven Python execution can look like: remote-first, wasm-secure, and community-built.
This feature is live in smolagents v1.20.0!
Try it out.
Break things. Extend it. Give us feedback.
Let's build safer, smarter agents; together π§ βοΈ
π https://github.com/huggingface/smolagents/releases/tag/v1.20.0
#smolagents #WebAssembly #Python #AIagents #Pyodide #Deno #OpenSource #HuggingFace #AgenticAI
We've just merged a major new capability into the smolagents framework: the CodeAgent can now execute Python code remotely in a secure, sandboxed WebAssembly environment!
π§ Powered by Pyodide and Deno, this new WasmExecutor lets your agent-generated Python code run safely: without relying on Docker or local execution.
Why this matters:
β Isolated execution = no host access
β No need for Python on the user's machine
β Safer evaluation of arbitrary code
β Compatible with serverless / edge agent workloads
β Ideal for constrained or untrusted environments
This is just the beginning: a focused initial implementation with known limitations. A solid MVP designed for secure, sandboxed use cases. π‘
π‘ We're inviting the open-source community to help evolve this executor:
β’ Tackle more advanced Python features
β’ Expand compatibility
β’ Add test coverage
β’ Shape the next-gen secure agent runtime
π Check out the PR: https://github.com/huggingface/smolagents/pull/1261
Let's reimagine what agent-driven Python execution can look like: remote-first, wasm-secure, and community-built.
This feature is live in smolagents v1.20.0!
Try it out.
Break things. Extend it. Give us feedback.
Let's build safer, smarter agents; together π§ βοΈ
π https://github.com/huggingface/smolagents/releases/tag/v1.20.0
#smolagents #WebAssembly #Python #AIagents #Pyodide #Deno #OpenSource #HuggingFace #AgenticAI
albertvillanovaΒ
posted
an
update
7 months ago
Post
1820
π SmolAgents v1.19.0 is live!
This release brings major improvements to agent flexibility, UI usability, streaming architecture, and developer experience: making it easier than ever to build smart, interactive AI agents. Here's what's new:
π§ Agent Upgrades
- Support for managed agents in ToolCallingAgent
- Context manager support for cleaner agent lifecycle handling
- Output formatting now uses XML tags for consistency
π₯οΈ UI Enhancements
- GradioUI now supports reset_agent_memory: perfect for fresh starts in dev & demos.
π Streaming Refactor
- Streaming event aggregation moved off the Model class
- β‘οΈ Better architecture & maintainability
π¦ Output Tracking
- CodeAgent outputs are now stored in ActionStep
- β More visibility and structure to agent decisions
π Bug Fixes
- Smarter planning logic
- Cleaner Docker logs
- Better prompt formatting for additional_args
- Safer internal functions and final answer matching
π Docs Improvements
- Added quickstart examples with tool usage
- One-click Colab launch buttons
- Expanded reference docs (AgentMemory, GradioUI docstrings)
- Fixed broken links and migrated to .md format
π Full release notes:
https://github.com/huggingface/smolagents/releases/tag/v1.19.0
π¬ Try it out, explore the new features, and let us know what you build!
#smolagents #opensource #AIagents #LLM #HuggingFace
This release brings major improvements to agent flexibility, UI usability, streaming architecture, and developer experience: making it easier than ever to build smart, interactive AI agents. Here's what's new:
π§ Agent Upgrades
- Support for managed agents in ToolCallingAgent
- Context manager support for cleaner agent lifecycle handling
- Output formatting now uses XML tags for consistency
π₯οΈ UI Enhancements
- GradioUI now supports reset_agent_memory: perfect for fresh starts in dev & demos.
π Streaming Refactor
- Streaming event aggregation moved off the Model class
- β‘οΈ Better architecture & maintainability
π¦ Output Tracking
- CodeAgent outputs are now stored in ActionStep
- β More visibility and structure to agent decisions
π Bug Fixes
- Smarter planning logic
- Cleaner Docker logs
- Better prompt formatting for additional_args
- Safer internal functions and final answer matching
π Docs Improvements
- Added quickstart examples with tool usage
- One-click Colab launch buttons
- Expanded reference docs (AgentMemory, GradioUI docstrings)
- Fixed broken links and migrated to .md format
π Full release notes:
https://github.com/huggingface/smolagents/releases/tag/v1.19.0
π¬ Try it out, explore the new features, and let us know what you build!
#smolagents #opensource #AIagents #LLM #HuggingFace
albertvillanovaΒ
posted
an
update
8 months ago
Post
744
New in smolagents v1.17.0:
- Structured generation in CodeAgent π§±
- Streamable HTTP MCP support π
- Agent.run() returns rich RunResult π¦
Smarter agents, smoother workflows.
Try it now: https://github.com/huggingface/smolagents/releases/tag/v1.17.0
- Structured generation in CodeAgent π§±
- Streamable HTTP MCP support π
- Agent.run() returns rich RunResult π¦
Smarter agents, smoother workflows.
Try it now: https://github.com/huggingface/smolagents/releases/tag/v1.17.0
albertvillanovaΒ
posted
an
update
8 months ago
Post
2609
New in smolagents v1.16.0:
π Bing support in WebSearchTool
π Custom functions & executor_kwargs in LocalPythonExecutor
π§ Streaming GradioUI fixes
π Local web agents via api_base & api_key
π Better docs
π https://github.com/huggingface/smolagents/releases/tag/v1.16.0
π Bing support in WebSearchTool
π Custom functions & executor_kwargs in LocalPythonExecutor
π§ Streaming GradioUI fixes
π Local web agents via api_base & api_key
π Better docs
π https://github.com/huggingface/smolagents/releases/tag/v1.16.0
albertvillanovaΒ
posted
an
update
9 months ago
Post
2891
smolagents v1.14.0 is out! π
π MCPClient: A sleek new client for connecting to remote MCP servers, making integrations more flexible and scalable.
πͺ¨ Amazon Bedrock: Native support for Bedrock-hosted models.
SmolAgents is now more powerful, flexible, and enterprise-ready. πΌ
Full release π https://github.com/huggingface/smolagents/releases/tag/v1.14.0
#smolagents #LLM #AgenticAI
π MCPClient: A sleek new client for connecting to remote MCP servers, making integrations more flexible and scalable.
πͺ¨ Amazon Bedrock: Native support for Bedrock-hosted models.
SmolAgents is now more powerful, flexible, and enterprise-ready. πΌ
Full release π https://github.com/huggingface/smolagents/releases/tag/v1.14.0
#smolagents #LLM #AgenticAI
anton-lΒ
authored
a
paper
9 months ago
albertvillanovaΒ
posted
an
update
10 months ago
Post
4195
π New smolagents update: Safer Local Python Execution! π¦Ύπ
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. π
Here's why this matters & what you need to know! π§΅π
1οΈβ£ Why is local execution risky? β οΈ
AI agents that run arbitrary Python code can unintentionally (or maliciously) access system files, run unsafe commands, or exfiltrate data.
2οΈβ£ New Safety Layer in smolagents π‘οΈ
We now inspect every return value during execution:
β Allowed: Safe built-in types (e.g., numbers, strings, lists)
β Blocked: Dangerous functions/modules (e.g., os.system, subprocess, exec, shutil)
3οΈβ£ Immediate Benefits π‘
- Prevent agents from accessing unsafe builtins
- Block unauthorized file or network access
- Reduce accidental security vulnerabilities
4οΈβ£ Security Disclaimer β οΈ
π¨ Despite these improvements, local Python execution is NEVER 100% safe. π¨
If you need true isolation, use a remote sandboxed executor like Docker or E2B.
5οΈβ£ The Best Practice: Use Sandboxed Execution π
For production-grade AI agents, we strongly recommend running code in a Docker or E2B sandbox to ensure complete isolation.
6οΈβ£ Upgrade Now & Stay Safe! π
Check out the latest smolagents release and start building safer AI agents today.
π https://github.com/huggingface/smolagents
What security measures do you take when running AI-generated code? Letβs discuss! π
#AI #smolagents #Python #Security
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. π
Here's why this matters & what you need to know! π§΅π
1οΈβ£ Why is local execution risky? β οΈ
AI agents that run arbitrary Python code can unintentionally (or maliciously) access system files, run unsafe commands, or exfiltrate data.
2οΈβ£ New Safety Layer in smolagents π‘οΈ
We now inspect every return value during execution:
β Allowed: Safe built-in types (e.g., numbers, strings, lists)
β Blocked: Dangerous functions/modules (e.g., os.system, subprocess, exec, shutil)
3οΈβ£ Immediate Benefits π‘
- Prevent agents from accessing unsafe builtins
- Block unauthorized file or network access
- Reduce accidental security vulnerabilities
4οΈβ£ Security Disclaimer β οΈ
π¨ Despite these improvements, local Python execution is NEVER 100% safe. π¨
If you need true isolation, use a remote sandboxed executor like Docker or E2B.
5οΈβ£ The Best Practice: Use Sandboxed Execution π
For production-grade AI agents, we strongly recommend running code in a Docker or E2B sandbox to ensure complete isolation.
6οΈβ£ Upgrade Now & Stay Safe! π
Check out the latest smolagents release and start building safer AI agents today.
π https://github.com/huggingface/smolagents
What security measures do you take when running AI-generated code? Letβs discuss! π
#AI #smolagents #Python #Security
- 2 replies
albertvillanovaΒ
posted
an
update
10 months ago
Post
4101
π Big news for AI agents! With the latest release of smolagents, you can now securely execute Python code in sandboxed Docker or E2B environments. π¦Ύπ
Here's why this is a game-changer for agent-based systems: π§΅π
1οΈβ£ Security First π
Running AI agents in unrestricted Python environments is risky! With sandboxing, your agents are isolated, preventing unintended file access, network abuse, or system modifications.
2οΈβ£ Deterministic & Reproducible Runs π¦
By running agents in containerized environments, you ensure that every execution happens in a controlled and predictable settingβno more environment mismatches or dependency issues!
3οΈβ£ Resource Control & Limits π¦
Docker and E2B allow you to enforce CPU, memory, and execution time limits, so rogue or inefficient agents donβt spiral out of control.
4οΈβ£ Safer Code Execution in Production π
Deploy AI agents confidently, knowing that any generated code runs in an ephemeral, isolated environment, protecting your host machine and infrastructure.
5οΈβ£ Easy to Integrate π οΈ
With smolagents, you can simply configure your agent to use Docker or E2B as its execution backendβno need for complex security setups!
6οΈβ£ Perfect for Autonomous AI Agents π€
If your AI agents generate and execute code dynamically, this is a must-have to avoid security pitfalls while enabling advanced automation.
β‘ Get started now: https://github.com/huggingface/smolagents
What will you build with smolagents? Let us know! ππ‘
Here's why this is a game-changer for agent-based systems: π§΅π
1οΈβ£ Security First π
Running AI agents in unrestricted Python environments is risky! With sandboxing, your agents are isolated, preventing unintended file access, network abuse, or system modifications.
2οΈβ£ Deterministic & Reproducible Runs π¦
By running agents in containerized environments, you ensure that every execution happens in a controlled and predictable settingβno more environment mismatches or dependency issues!
3οΈβ£ Resource Control & Limits π¦
Docker and E2B allow you to enforce CPU, memory, and execution time limits, so rogue or inefficient agents donβt spiral out of control.
4οΈβ£ Safer Code Execution in Production π
Deploy AI agents confidently, knowing that any generated code runs in an ephemeral, isolated environment, protecting your host machine and infrastructure.
5οΈβ£ Easy to Integrate π οΈ
With smolagents, you can simply configure your agent to use Docker or E2B as its execution backendβno need for complex security setups!
6οΈβ£ Perfect for Autonomous AI Agents π€
If your AI agents generate and execute code dynamically, this is a must-have to avoid security pitfalls while enabling advanced automation.
β‘ Get started now: https://github.com/huggingface/smolagents
What will you build with smolagents? Let us know! ππ‘
anton-lΒ
authored
a
paper
11 months ago
albertvillanovaΒ
posted
an
update
11 months ago
Post
4192
π Introducing
@huggingface
Open Deep-Researchπ₯
In just 24 hours, we built an open-source agent that:
β Autonomously browse the web
β Search, scroll & extract info
β Download & manipulate files
β Run calculations on data
55% on GAIA validation set! Help us improve it!π‘
https://huggingface.co/blog/open-deep-research
In just 24 hours, we built an open-source agent that:
β Autonomously browse the web
β Search, scroll & extract info
β Download & manipulate files
β Run calculations on data
55% on GAIA validation set! Help us improve it!π‘
https://huggingface.co/blog/open-deep-research
- 3 replies
albertvillanovaΒ
posted
an
update
about 1 year ago
Post
2224
Discover all the improvements in the new version of Lighteval: https://huggingface.co/docs/lighteval/
lhoestqΒ
authored
a
paper
about 1 year ago
Post
3665
Introducing ππ
π’π§πππππ‘: the best public math pre-training dataset with 50B+ tokens!
HuggingFaceTB/finemath
Math remains challenging for LLMs and by training on FineMath we see considerable gains over other math datasets, especially on GSM8K and MATH.
We build the dataset by:
π οΈ carefully extracting math data from Common Crawl;
π iteratively filtering and recalling high quality math pages using a classifier trained on synthetic annotations to identify math reasoning and deduction.
We conducted a series of ablations comparing the performance of Llama-3.2-3B-Base after continued pre-training on FineMath and observe notable gains compared to the baseline model and other public math datasets.
We hope this helps advance the performance of LLMs on math and reasoning! π
Weβre also releasing all the ablation models as well as the evaluation code.
HuggingFaceTB/finemath-6763fb8f71b6439b653482c2
HuggingFaceTB/finemath
Math remains challenging for LLMs and by training on FineMath we see considerable gains over other math datasets, especially on GSM8K and MATH.
We build the dataset by:
π οΈ carefully extracting math data from Common Crawl;
π iteratively filtering and recalling high quality math pages using a classifier trained on synthetic annotations to identify math reasoning and deduction.
We conducted a series of ablations comparing the performance of Llama-3.2-3B-Base after continued pre-training on FineMath and observe notable gains compared to the baseline model and other public math datasets.
We hope this helps advance the performance of LLMs on math and reasoning! π
Weβre also releasing all the ablation models as well as the evaluation code.
HuggingFaceTB/finemath-6763fb8f71b6439b653482c2
Post
2978
Made a HF Dataset editor a la gg sheets here:
lhoestq/dataset-spreadsheets
With Dataset Spreadsheets:
βοΈ Edit datasets in the UI
π Share link with collaborators
π Use locally in DuckDB or Python
Available for the 100,000+ parquet datasets on HF :)
With Dataset Spreadsheets:
βοΈ Edit datasets in the UI
π Share link with collaborators
π Use locally in DuckDB or Python
Available for the 100,000+ parquet datasets on HF :)
albertvillanovaΒ
posted
an
update
about 1 year ago
Post
1935
π¨ How green is your model? π± Introducing a new feature in the Comparator tool: Environmental Impact for responsible #LLM research!
π open-llm-leaderboard/comparator
Now, you can not only compare models by performance, but also by their environmental footprint!
π The Comparator calculates COβ emissions during evaluation and shows key model characteristics: evaluation score, number of parameters, architecture, precision, type... π οΈ
Make informed decisions about your model's impact on the planet and join the movement towards greener AI!
π open-llm-leaderboard/comparator
Now, you can not only compare models by performance, but also by their environmental footprint!
π The Comparator calculates COβ emissions during evaluation and shows key model characteristics: evaluation score, number of parameters, architecture, precision, type... π οΈ
Make informed decisions about your model's impact on the planet and join the movement towards greener AI!
albertvillanovaΒ
posted
an
update
about 1 year ago
Post
1679
π New feature of the Comparator of the π€ Open LLM Leaderboard: now compare models with their base versions & derivatives (finetunes, adapters, etc.). Perfect for tracking how adjustments affect performance & seeing innovations in action. Dive deeper into the leaderboard!
π οΈ Here's how to use it:
1. Select your model from the leaderboard.
2. Load its model tree.
3. Choose any base & derived models (adapters, finetunes, merges, quantizations) for comparison.
4. Press Load.
See side-by-side performance metrics instantly!
Ready to dive in? π Try the π€ Open LLM Leaderboard Comparator now! See how models stack up against their base versions and derivatives to understand fine-tuning and other adjustments. Easier model analysis for better insights! Check it out here: open-llm-leaderboard/comparator π
π οΈ Here's how to use it:
1. Select your model from the leaderboard.
2. Load its model tree.
3. Choose any base & derived models (adapters, finetunes, merges, quantizations) for comparison.
4. Press Load.
See side-by-side performance metrics instantly!
Ready to dive in? π Try the π€ Open LLM Leaderboard Comparator now! See how models stack up against their base versions and derivatives to understand fine-tuning and other adjustments. Easier model analysis for better insights! Check it out here: open-llm-leaderboard/comparator π