Run production AI agents in n8n with Amazon Bedrock AgentCore harness
Machine Learning Blog
This article explains how to use the new Amazon Bedrock AgentCore community node for n8n to build production AI agents with persistent memory, tools, and multi-provider model support directly in the n8n visual editor.
- AgentCore harness provides orchestration, tool management, context handling, and state persistence that production agents require
- The open-source n8n node (@aws/n8n-nodes-agentcore) integrates the harness into n8n workflows with familiar AWS credential patterns
- Build agents with persistent conversation memory, per-user memory scoping using Actor IDs, and code interpreter tools
- Load skills from AWS curated catalog, Git repositories, or S3 to give agents domain knowledge on demand
- Run agents privately in your VPC with managed container images and VPC endpoints for ECR and S3
- Support for Amazon Bedrock, OpenAI, Google Gemini, and LiteLLM providers with mid-session switching capability
The node enables developers to create sophisticated production agents without writing infrastructure or agent orchestration code, with examples and templates available in the GitHub repository.
The AWS News Feed is currently looking for gold sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.
Related articles
2026
2025
2026
2026
The AWS News Feed is currently looking for silver sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.