AI product Open source
Amazon Bedrock AgentCore is an AWS service for deploying and operating AI agents in production. It provides a framework- and model-agnostic runtime for agents built with systems such as Strands Agents, CrewAI, LangGraph, LlamaIndex, Google ADK, or OpenAI Agents, with support for Python and TypeScript applications.
Its capabilities include managed agent runtime hosting, sessions, memory, identity and access management, a gateway for turning APIs, Lambda functions, and services into MCP-compatible tools, built-in tools such as code execution and web search, and OpenTelemetry-based observability for tracing, debugging, and monitoring. The linked AWS Labs repository provides sample applications, tutorials, deployment templates, integrations, and blueprints covering these capabilities.
The AgentCore CLI scaffolds projects, supports local development with hot reload and local invocation, and deploys agents to AWS with commands such as `agentcore deploy` and `agentcore invoke`. The samples repository is licensed under Apache 2.0.
3 uses taken from transcripts — each links to the moment in the video.
An AWS service for putting agents into production. It provides a runtime container that hosts agentic applications from any framework, with built-in sessions (up to 8 hours), agentic observability in CloudWatch, memory, a gateway for tools and MCP endpoints, automatic scaling, and deployment via a couple of CLI commands.
A repository of AgentCore samples linked by the speakers, containing reference code for deploying agents to Amazon Bedrock AgentCore.
AWS's sandbox hosting platform for agents, providing runtime environments, sandboxes, identity, memory, and gateways for building and hosting agents on the cloud. The talk describes stress-testing its code sandbox and cloud browser.
2 in the library.