Welcome, Gradio 5
Hugging Face announces Gradio 5, a major version release of its popular ML demo and application framework. The release likely includes significant updates to the tooling used by researchers and developers to build and share AI/ML interfaces. Gradio is widely used in the AI community for rapid prototyping and model demonstrations.
Related guides (3)
Related events (8)
A Security Review of Gradio 5
Hugging Face published a security review of Gradio 5, examining vulnerabilities and mitigations in the popular ML demo and deployment framework. The post covers security improvements made in the version 5 release cycle. As Gradio is widely used for deploying AI/ML models and building interactive demos, its security posture directly affects the broader ML tooling ecosystem.
Five Big Improvements to Gradio MCP Servers
Hugging Face's Gradio team has announced five significant updates to Gradio's Model Context Protocol (MCP) server support. The improvements aim to make it easier to build and deploy MCP-compatible AI tool servers using Gradio. This is relevant to the growing agent-tool ecosystem where MCP is emerging as a standard protocol for connecting AI models to external tools and data sources.
Gradio 3.0 Released with Blocks API
Gradio 3.0 introduces a new Blocks API that gives developers fine-grained control over layout and event handling in ML demo interfaces. The release represents a significant redesign of the popular open-source tool used to build and share machine learning demos. Blocks enables more complex, multi-step interactive applications compared to the previous Interface abstraction.
How to Build an MCP Server with Gradio
Hugging Face published a tutorial on building Model Context Protocol (MCP) servers using Gradio, enabling AI models to expose tools and resources through the MCP standard. The post demonstrates how Gradio applications can serve as MCP-compatible backends, allowing AI agents to discover and invoke Gradio-hosted functions. This lowers the barrier for ML practitioners to participate in the emerging MCP ecosystem without deep protocol knowledge.
Gradio-Lite: Serverless Gradio Running Entirely in Your Browser
Gradio-Lite enables running Gradio ML demo applications entirely in the browser using Pyodide (Python compiled to WebAssembly), eliminating the need for a server backend. This allows developers to embed interactive ML interfaces directly in static web pages with no infrastructure costs. The approach leverages WebAssembly to execute Python and ML inference client-side, though with limitations on supported libraries and performance.
Upskill your LLMs With Gradio MCP Servers
Hugging Face published a blog post explaining how to build Model Context Protocol (MCP) servers using Gradio, enabling LLMs to access custom tools and external capabilities. The post covers how Gradio applications can be exposed as MCP-compatible tool endpoints that AI agents can invoke. This positions Gradio as part of the growing MCP ecosystem for extending LLM functionality with structured tool use.
GGML and llama.cpp Join Hugging Face to Ensure Long-Term Progress of Local AI
GGML and llama.cpp, the foundational open-source libraries enabling efficient local inference of large language models, are joining Hugging Face. This move is intended to secure long-term development and sustainability of the projects that underpin much of the local/on-device AI ecosystem. The acquisition or integration represents a significant consolidation of key open-weights inference infrastructure under the Hugging Face umbrella.
GLM-5.2 announced as model built for long-horizon tasks
ZAI.org published a blog post on Hugging Face announcing GLM-5.2, a model positioned for long-horizon tasks. The post appears to be a model release announcement from the GLM (General Language Model) lineage. Limited body content is available, but the framing suggests capabilities relevant to extended reasoning or agentic workflows.