Run production AI agents in n8n with Amazon Bedrock AgentCore harness
Amazon Bedrock AgentCore harness is now generally available with an n8n community node
“AgentCore harness gives you that layer as a managed capability. You define an agent in configuration, including the model it uses, the tools it calls, the skills it has access to, and the instructions it follows, and AgentCore assembles and runs the loop for you.”
AWS has made Amazon Bedrock AgentCore harness generally available, with a new open-source n8n community node that brings production agent infrastructure — persistent memory, tool use, session isolation — into n8n's visual workflow editor. The offering is model-agnostic, supporting Bedrock, OpenAI, Gemini, and LiteLLM providers within the same conversation. This matters as it lowers the barrier to production-grade agentic workflows for no-code/low-code builders, but is primarily an integration announcement rather than a foundational architectural shift.