MCP App StoreLe meilleur de l'écosystème IA et MCP, sélectionné chaque jour.
Sources
Hugging Face introduces OpenEnv, a new initiative to create an open-standard environment for AI agents. This aims to standardize how agents interact with tools and environments, fostering a more interoperable agent ecosystem.
Hugging Face and VirusTotal are partnering to improve AI model security by scanning for malicious files and vulnerabilities in model weights. This collaboration aims to create a safer ecosystem for sharing and deploying open-source AI models.
The Sentence Transformers library is officially integrating with Hugging Face to streamline the creation and sharing of embedding models. This move simplifies the workflow for developers building RAG systems and semantic search applications.
OpenAI has launched ChatGPT Atlas, a dedicated browser for MacOS with integrated AI capabilities. It provides instant answers and summaries directly from any webpage with user-controlled privacy settings.
Anthropic launched Claude Code on the web, letting users delegate coding tasks directly from the browser without a local CLI install. Tasks run on Anthropic-managed cloud infrastructure, making it easy to tackle bug backlogs and routine fixes without setting up a local environment. Now in beta as a research preview.
Claude Code gained filesystem and network sandboxing, letting it run autonomously with fewer permission interruptions while remaining safe. The sandboxing isolates risky operations so Claude can proceed confidently without asking the user about every file write or network call. A key step in making agentic coding tools both safer and less annoying to use.
Anthropic details their approach to building modular 'Agent Skills' that enable AI agents to perform complex real-world tasks with higher reliability and effectiveness.
Intel and Hugging Face provide a streamlined 3-step guide to deploying Vision Language Models (VLMs) on Intel CPUs using OpenVINO. This lowers the barrier for running multi-modal AI on commodity hardware without requiring high-end GPUs.
OpenAI used Codex internally to build experiences, demos, and products for their DevDay 2025 event — eating their own cooking at scale. The post reveals which parts of the event infrastructure were Codex-generated and the workflows they used. Interesting as a signal for what Codex can reliably ship in a high-stakes, time-constrained environment.
OpenAI introduces new real-world testing methods to evaluate and reduce political bias in ChatGPT. The focus is on improving objectivity through more rigorous evaluation frameworks.
BigCodeArena introduces a method for judging LLM code generation by executing the code end-to-end. This provides a more rigorous evaluation metric than token-based similarity.
OpenAI Codex is now generally available, introducing a Slack integration and a dedicated SDK. These updates, along with new admin tools and usage dashboards, make it significantly easier for developers to deploy and manage Codex at scale.
OpenAI introduces a new Apps SDK in preview, allowing developers to build integrated apps directly within ChatGPT. This expands the agentic capabilities of the platform and provides a new way for developers to distribute AI-powered tools.
OpenAI releases AgentKit, expanded evaluations, and reinforcement fine-tuning (RFT) to help developers move agentic prototypes to production more efficiently.
Claude is now natively integrated with Slack, allowing teams to get help directly in channels and threads without leaving their workspace. You can also connect your Slack workspace to Claude.ai so it can search conversations and pull relevant context when needed. A significant step for enterprise teams already living in Slack.
Hugging Face introduces RTEB, a new benchmark standard for evaluating retrieval systems. This provides developers with a more robust framework to measure and improve the accuracy of AI retrieval pipelines.
OpenAI released Sora 2, featuring improved physical accuracy, realism, and controllability. The new model introduces synchronized dialogue and sound effects, available via a dedicated Sora app.
OpenAI introduces Sora 2 and the Sora app, focusing on safety frameworks and concrete protections for state-of-the-art video generation.
OpenAI releases the system card for Sora 2, detailing a new state-of-the-art video and audio generation model. It introduces significant improvements in physics accuracy, realism, and synchronized audio.
OpenAI developed a specialized system to extract and structure contract data, significantly reducing manual turnaround times. This implementation demonstrates a practical application of AI agents for high-precision document processing.