Your agents are only as trustworthy as what they consume, build, and ship. JFrog governs every AI model, agent skill, MCP server, AI-generated code, and assembled artifact in a single source of truth.
Secure your entire agentic software supply chain so you can ship trusted software at your new speed.
A developer on your team just told Claude Code to connect to a new MCP server, the protocol coding agents use to reach organizational tools and data. Nobody in security reviewed it. Nobody in security even knows it happened. For two-thirds of enterprises, the primary obstacle to scaling agentic development isn’t budget or headcount — …
UPDATE August 5, 2026: This week at Black Hat USA, the OpenAI team presented a detailed reconstruction of the chain of events behind the Hugging Face incident. I was glad to watch OpenAI speaking openly about it. This kind of transparency reflects the same spirit of collaboration we experienced working with their team behind the …
AI agents are part of the modern development workflow. They write code, review pull requests, generate tests, call tools, interact with MCP servers, and help developers move faster. But behind every useful agent, there is something just as important as the model itself: the context that tells the agent how to behave. That context can …
Machine learning models are not like other software artifacts. A single fine-tuned LLM can weigh 70 GB. A model family may share 95% of its weights across dozens of variants. When hundreds of developers, training jobs, and GPU clusters all need the same model at the same time, the infrastructure underneath needs to be built …
AI coding agents are changing the pace of software development. With tools like Claude Code, developers can move from idea to implementation faster than ever, generating code, exploring unfamiliar repositories, refactoring services, and turning plain-language intent into working software. That speed is powerful. But speed without governance = risk. It also creates a new challenge: …
The software supply chain is no longer just about shipping code, it is about managing intelligence and risk. As DevOps, DevSecOps, DevGovOps and AI/ML practices converge into a single AI-driven and increasingly agentic delivery pipeline, the demands on development and security teams have reached a new level. The platform that once managed packages and artifacts …
Editors Note: the JFrog Kubelet Credential Provider now supports Google Kubernetes Engine (GKE), Azure Kubernetes Service (AKS), and Amazon EKS including projected tokens (KEP-4412 enhancement). This blog is updated to reflect these capabilities. Amazon EKS, GKE, and AKS are fully managed, compliant Kubernetes services that simplify running, managing, and scaling containerized applications. These services automatically …
In my previous posts, we discussed the where and the how of managing your ML assets. We showed you how JFrog Artifactory acts as a powerful, universal model registry (the “where”) and how the FrogML SDK serves as the gateway to get your models and metadata into it (the “how”). Now, let’s talk about the …
The Wake-Up Call The rapid rise of artificial intelligence, more specifically, generative AI systems such as OpenAI’s ChatGPT, has simultaneously spurred intense development and concern over the past year. On the 30th of October, President Joe Biden signed an Executive Order that urges new federal standards for AI development, safety, security, and trustworthiness that also …
JFrog’s new log analytics integration with New Relic brings together powerful observability capabilities to monitor, analyze, and visualize logs and metrics from self-hosted JFrog environments. The integration is free for all tiers of self-hosted JFrog customers and utilizes the powerful, open source log management tool, Fluentd, to collect, process, and surface data in New Relic …
NVIDIA 
Cursor 
GitHub 
Docker 
Maven 
Financial Services 
Public Sector 
Technology 
Healthcare 
Gaming 
Automotive 
Enterprise 
