AWS Open Source Blog
Category: Artificial Intelligence
Introducing Strands Agents 1.0: Production-Ready Multi-Agent Orchestration Made Simple
Today we are excited to announce version 1.0 of the Strands Agents SDK, marking a significant milestone in our journey to make building AI agents simple, reliable, and production-ready. Strands Agents is an open source SDK that takes a model-driven approach to building and running AI agents in just a few lines of code. Strands […]
Open Protocols for Agent Interoperability Part 3: Strands Agents & MCP
Developers are architecting and building systems of AI agents that work together to autonomously accomplish users’ tasks. In Part 1 of our blog series on Open Protocols for Agent Interoperability we covered how Model Context Protocol (MCP) can be used to facilitate inter-agent communication and the MCP specification enhancements AWS is working on to enable […]
Open Protocols for Agent Interoperability Part 2: Authentication on MCP
In Part 1 of our blog series on Open Protocols for Agent Interoperability we covered how the Model Context Protocol (MCP) can be used to facilitate inter-agent communication and the MCP specification enhancements AWS is working on to enable that. In Part 2 of this blog series we dive deep into authentication in the latest […]
Using Strands Agents with Claude 4 Interleaved Thinking
When we introduced the Strands Agents SDK, our goal was to make agentic development simple and flexible by embracing a model-driven approach. Today, we’re excited to highlight how you can use Claude 4’s interleaved thinking beta feature with Strands to further simplify how you write AI agents to solve complex tasks with tools. With a […]
Open Protocols for Agent Interoperability Part 1: Inter-Agent Communication on MCP
At AWS, open standards run deep in our DNA, driving all that we do. That’s why we decided to build Amazon Elastic Cloud Compute (EC2) as a protocol-agnostic cloud computing service and Amazon SageMaker as a framework-agnostic deep learning service. Our commitment to openness continues as we enter the agentic AI era, extending to inter-agent […]
Introducing Strands Agents, an Open Source AI Agents SDK
Today I am happy to announce we are releasing Strands Agents. Strands Agents is an open source SDK that takes a model-driven approach to building and running AI agents in just a few lines of code. Strands scales from simple to complex agent use cases, and from local development to deployment in production. Multiple teams […]
Deploy Large Language Models Easily with the New ezsmdeploy Python SDK
Announcing ezsmdeploy v2.0!
Ray Integration for AWS Trainium and AWS Inferentia is Now Available
AWS Trainium and AWS Inferentia are now integrated with open source Ray on Amazon Elastic Compute Cloud (EC2).
Root Cause Analysis with DoWhy, an Open Source Python Library for Causal Machine Learning
The root cause analysis (RCA) features of the DoWhy open source Python library is an automated tool to simplify and help identify the root causes of observed changes in complex systems.
Twin Neural Network Training with PyTorch and Fast.ai and its Deployment with TorchServe on Amazon SageMaker
In this post we demonstrate how to train a Twin Neural Network based on PyTorch and Fast.ai, and deploy it with TorchServe on Amazon SageMaker inference endpoint. For demonstration purposes, we build an interactive web application for users to upload images and make inferences from the trained and deployed model, based on Streamlit, which is an open source framework for data scientists to efficiently create interactive web-based data applications in pure Python.