HF Agent
🤖
9
Chat with an AI assistant to get answers and help
smolagents
Team
community
AI & ML interests
None defined yet.
Recent Activity
tfrere
updated a Space about 21 hours ago
akseljoonas
updated a Space 5 days ago
Post
3420
Hugging Face MCP Server v0.3.2
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- Replace model_search and dataset_search with combined hub_repo_search tool.
- Less distracting description for hf_doc_search
- model_search and dataset_search tool calls will still function (plan to remove next release).
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- Replace model_search and dataset_search with combined hub_repo_search tool.
- Less distracting description for hf_doc_search
- model_search and dataset_search tool calls will still function (plan to remove next release).
- 4 replies
ui updates
#1 opened 9 days ago
by
akseljoonas
lewtun
submitted a paper to Daily Papers 11 days ago
lewtun
submitted a paper to Daily Papers 13 days ago
albertvillanova
posted an
update 14 days ago
Post
1634
5 years already working in democratizing AI 🤗
Grateful to be part of such an awesome team making it happen every day.
Grateful to be part of such an awesome team making it happen every day.
Post
846
Interesting article: use Claude Code to help open models write CUDA kernels (for eg) by turning CC traces into Skills. They made a library out of it 👀
https://huggingface.co/blog/upskill
https://huggingface.co/blog/upskill
Post
286
Hugging Face MCP Server v0.3.1
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- Streamable HTTP used for Gradio Connectivity
- SSE Transport (as Server) removed
- Proxy Configuration added for launch of sub-agent tools
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- Streamable HTTP used for Gradio Connectivity
- SSE Transport (as Server) removed
- Proxy Configuration added for launch of sub-agent tools
Post
3433
Nvidia is on a roll lately. Nemotron 3 Nano is my new fav local model, but here's the real flex: they published the entire evaluation setup. Configs, prompts, logs, all of it. This is how you do open models 🔥
https://huggingface.co/blog/nvidia/nemotron-3-nano-evaluation-recipe
https://huggingface.co/blog/nvidia/nemotron-3-nano-evaluation-recipe
Post
2543
Hugging Face MCP Server v0.2.46
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- Add "discover" to Dynamic Space tool. Recommend deselecting "space_search" if using dynamic spaces.
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- Add "discover" to Dynamic Space tool. Recommend deselecting "space_search" if using dynamic spaces.
Post
3028
Hugging Face MCP Server v0.2.45
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- New! Experimental dynamic_space tool.
- Default Image Generator changed to Qwen-Image-Fast
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- New! Experimental dynamic_space tool.
- Default Image Generator changed to Qwen-Image-Fast
abidlabs
authored 2 papers 3 months ago
abidlabs
authored a paper 4 months ago
Post
2259
Hugging Face MCP Server v0.2.40
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Improved progressive disclosure and descriptions for Jobs tool.
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Improved progressive disclosure and descriptions for Jobs tool.
Post
9858
Why I think local, open-source models will eventually win.
The most useful AI applications are moving toward multi-turn agentic behavior: systems that take hundreds or even thousands of iterative steps to complete a task, e.g. Claude Code, computer-control agents that click, type, and test repeatedly.
In these cases, the power of the model is not how smart it is per token, but in how quickly it can interact with its environment and tools across many steps. In that regime, model quality becomes secondary to latency.
An open-source model that can call tools quickly, check that the right thing was clicked, or verify that a code change actually passes tests can easily outperform a slightly “smarter” closed model that has to make remote API calls for every move.
Eventually, the balance tips: it becomes impractical for an agent to rely on remote inference for every micro-action. Just as no one would tolerate a keyboard that required a network request per keystroke, users won’t accept agent workflows bottlenecked by latency. All devices will ship with local, open-source models that are “good enough” and the expectation will shift toward everything running locally. It’ll happen sooner than most people think.
The most useful AI applications are moving toward multi-turn agentic behavior: systems that take hundreds or even thousands of iterative steps to complete a task, e.g. Claude Code, computer-control agents that click, type, and test repeatedly.
In these cases, the power of the model is not how smart it is per token, but in how quickly it can interact with its environment and tools across many steps. In that regime, model quality becomes secondary to latency.
An open-source model that can call tools quickly, check that the right thing was clicked, or verify that a code change actually passes tests can easily outperform a slightly “smarter” closed model that has to make remote API calls for every move.
Eventually, the balance tips: it becomes impractical for an agent to rely on remote inference for every micro-action. Just as no one would tolerate a keyboard that required a network request per keystroke, users won’t accept agent workflows bottlenecked by latency. All devices will ship with local, open-source models that are “good enough” and the expectation will shift toward everything running locally. It’ll happen sooner than most people think.
- 8 replies
Post
370
Hugging Face MCP Server v0.2.35
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
$HF_TOKEN is expanded in Jobs Secrets environment variables.
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
$HF_TOKEN is expanded in Jobs Secrets environment variables.
andito
authored a paper 4 months ago
Post
361
Hugging Face MCP Server v0.2.33
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Allow discovery of Product Documentation Library via the Search tool.
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Allow discovery of Product Documentation Library via the Search tool.