# agentcore runtime Published articles for agentcore runtime. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## The new AgentCore runtime: Elastic, optimized, and consistently fast starts DevFeed: [The new AgentCore runtime: Elastic, optimized, and consistently fast starts]() Original publisher: [Read original article]() Author: Evandro Franco Published: 2026-09-18T15:31:34Z Content type: release Language: en Sources: [Artificial Intelligence]() Topics: [Amazon Bedrock AgentCore](), [Amazon Bedrock](), [Serverless](), [Concurrency]() Tags: [agentcore-runtime](), [agents](), [amazon-bedrock](), [amazon-bedrock-agentcore](), [announcements](), [concurrency](), [efficiency](), [elastic](), [expert-400](), [infrastructure](), [long-running](), [optimized](), [production](), [runtime](), [sessions](), [speed]() ### AI overview Amazon announces a new AgentCore runtime for production AI agents. The managed compute layer improves memory reclamation, cold-start consistency across image sizes and concurrency levels, elasticity, and usage-based cost efficiency. ### Source excerpt Today we are announcing the new AgentCore runtime, a capability of Amazon Bedrock AgentCore built for the speed, flexibility, and cost efficiency that production agents demand. It reclaims memory as sessions release it and delivers consistent cold starts regardless of image size or concurrency. ## Security Analysis of AWS AgentCore Harness Credential Exposure Through Prompt Injection DevFeed: [Security Analysis of AWS AgentCore Harness Credential Exposure Through Prompt Injection]() Original publisher: [Read original article]() Author: Niv Rabin Published: 2026-09-18T10:00:36Z Content type: article Language: en Sources: [Unit 42]() Topics: [prompt injection](), [cloud security](), [Artificial Intelligence](), [Security](), [least privilege](), [AWS IAM](), [Model Context Protocol]() Tags: [agentcore-runtime](), [agentic-ai](), [ai-agents](), [aws](), [cloud](), [cloud-cybersecurity-research](), [cloud-security](), [encryption](), [exfiltration](), [iam](), [identity-and-access-management](), [least-privilege](), [mcp-server](), [prompt-injection](), [sandbox](), [shell-tool](), [threat-research]() ### AI overview Unit 42 researchers found that default configurations in AWS AgentCore Harness could allow prompt injection to steer an agent and exfiltrate plaintext credentials managed by AgentCore Identity. The analysis examines the interaction between the identity vault, a downstream MCP server, and the harness's built-in shell tool. It recommends restricting allowed tools, applying least privilege to identity-vault service accounts, and monitoring outbound traffic. ### Source excerpt Analysis of how default configurations in AWS AgentCore Harness allow prompt injection to exfiltrate credentials, and key steps to secure your agents. The post A Vault with a Heap-View: The Uncomfortable Space Between AgentCore Harness and Identity appeared first on Unit 42. ## Building and Deploying .NET AI Agents with Amazon Bedrock AgentCore DevFeed: [Building and Deploying .NET AI Agents with Amazon Bedrock AgentCore]() Original publisher: [Read original article]() Author: Philippe El Asmar Published: 2026-08-05T16:56:46Z Content type: tutorial Language: en Sources: [AWS Developer Tools Blog]() Topics: [Amazon Bedrock AgentCore](), [.NET](), [Artificial Intelligence](), [Microsoft Agent Framework](), [ASP.NET Core](), [Model Context Protocol](), [Scalability](), [container]() Tags: [agentcore-runtime](), [ai](), [ai-agents](), [amazon-bedrock-agentcore](), [announcement](), [announcements](), [asp-net](), [asp-net-core](), [aws](), [aws-sdk-for-net](), [container](), [memory](), [microsoft-agent-framework](), [model-context-protocol](), [net](), [routing](), [scaling]() ### AI overview This tutorial explains how to build and deploy .NET AI agents with Amazon Bedrock AgentCore. It describes the managed runtime's operational features, the AWS.AgentCore.Hosting .NET library, integration with Microsoft Agent Framework and MCP, and source-generator and extension-method approaches for configuring ASP.NET Core applications. ### Source excerpt Amazon Bedrock AgentCore is a managed service for running AI agents in production. You bring your agent code packaged as a container, and Bedrock AgentCore handles the operational concerns: scaling, session routing, health checking, and providing managed capabilities like conversation memory. AWS.AgentCore.Hosting is the .NET library that connects your agent code to this service. It [...]