@aws-open-source-blog
Publisher
21
Posts
If you are building AI agents, you have likely encountered a growing list of protocol acronyms—MCP, A2A, UTCP, AG-UI, and x402—that can feel overwhelming. The open source community has converged on several complementary protocols. An AI agent is only as useful as the systems it can reach: interna...
As organizations move to adopt agentic capabilities to accelerate their business objectives, they are challenged with enabling those capabilities within a security and governance framework that complies with enterprise requirements. Some organizations lean into the promise of serverless capabilit...
Today, we are launching an open source Model Context Protocol (MCP) server that brings AI-powered dataset discovery to Registry of Open Data on AWS (RODA). As of today, RODA hosts over 1,100 high-value datasets from more than 400 organizations, spanning satellite imagery, life sciences, climate,...
IT support teams face a persistent challenge: employees expect instant answers to common questions (VPN setup, single sign-on troubleshooting, new-hire onboarding), but novel or complex issues still require human expertise. An AI agent that confidently answers, “How do I reset my VPN?” but halluc...
MySQL — the open source database behind millions of applications worldwide — is opening a new chapter. Today, Oracle announced a community governance model for MySQL that creates pathways for the broader community to participate in the project’s development and direction. This post explains why A...
Enterprises that onboard AI assets (MCP servers, agents, skills, and multi-step workflows) need to govern these assets and make them discoverable without blocking innovation. Central IT maintains a list of approved MCP servers and skills for the organization. Each line of business also publishes...
Today, we’re announcing Trusted Remote Execution (Rex, for short) — an open source scripting runtime where every system operation is authorized by policy. Scripts are written in Rhai, a lightweight language with no built-in system access. The only way to reach the host is through operations Rex e...
As organizations scale applications, managing authorization becomes increasingly complex. What starts as role-based permissions quickly evolves into intricate rules spanning multiple services, regions, and compliance requirements. Traditional approaches of embedding authorization logic in applica...
Introduction Organizations in automotive, manufacturing, and embedded systems increasingly rely on cloud-based development environments to reduce hardware dependency and accelerate software delivery. As vehicle architectures shift toward software-defined platforms, engineering teams need access t...
The security industry stands at an inflection point. In November 2024, the Open Cybersecurity Schema Framework (OCSF) joined the Linux Foundation, cementing its role as a vendor-neutral, open source standard for the global security community. Last summer at Black Hat 2025, we showed you how OCSF...
AWS, Anthropic, Google, Microsoft, and OpenAI today announced a joint $12.5 million investment with the Linux Foundation to help open source projects address a surge in AI-enhanced and AI-generated security vulnerability reports. Both the Alpha Omega initiative and the Open Source Security Founda...
We’re introducing Strands Labs, a new Strands GitHub organization designed to give developers the ability to get hands-on with experimental, state-of-the-art approaches to agentic AI development. The Strands Agents SDK – available for both Python and TypeScript – has gained incredible traction in...
Cedar, an open source authorization policy language and SDK, has joined the Cloud Native Computing Foundation (CNCF) as a Sandbox project. CNCF provides a neutral home for early stage and developing open source projects. Cedar fulfills the need for a fast, safe, and analyzable authorization polic...
Agentic AI systems are rapidly expanding beyond the digital world and into the physical, where AI agents perceive, reason, and act in real environments. As AI systems increasingly interact with the physical world through robotics, autonomous vehicles, and smart infrastructure, a fundamental quest...
AWS is excited to continue our support for Model Context Protocol (MCP) as it moves under the Linux Foundation. This move enables us, our partners, and our customers to be more confident in the long-term success of the protocol which has become a standard component of agentic architectures. By...
Modern AI can write code, compose symphonies, and solve complex reasoning problems. So why is it still so hard to get them to reliably do what you want? Building reliable AI agents that consistently perform complex tasks remains challenging. While modern language models excel at reasoning and pro...
AWS is excited to announce the awslabs/ml-container-creator open source project to simplify the process of building and deploying custom machine learning models on Amazon SageMaker. Some customers face challenges when trying to leverage the bring-your-own-container (BYOC) paradigm for hosting the...
We’re excited to share that the Swift AWS Lambda Runtime project has officially moved to the AWS Labs organization. You can now find it here: ? https://github.com/awslabs/swift-aws-lambda-runtime This move marks a new chapter for the project, while maintaining full continuity with its roots. A th...
Jupyter notebooks have become a popular tool for data scientists, researchers, educators and analysts who need to experiment with code, visualize data, and document their findings. Many users run Jupyter on their laptops. This creates limitations to collaborate with a distributed team because use...
Today we are introducing CLI Agent Orchestrator (CAO, pronounced “kay-oh”), an open source, multi-agent orchestration framework that transforms how developers work with AI-powered CLI tools such as Amazon Q CLI and Claude Code. While individual developer CLI tools excel at focused tasks with soph...
Until recently, building AI agents meant wrestling with complex orchestration frameworks. Developers wrote elaborate state machines, predefined workflows, and extensive error-handling code to guide language models through multi-step tasks. We needed to build elaborate decision trees to handle “wh...
