N8n – Flexible AI workflow automation for technical teams(n8n.io) Build with the precision of code or the speed of drag-n-drop. Host with on-prem control or in-the-cloud convenience. n8n gives you more freedom to implement multi-step AI agents and integrate apps than any other tool.
LLM Workflows then Agents: Getting Started with Apache Airflow(github.com/astronomer) This repository contains an SDK for working with LLMs from Apache Airflow, based on Pydantic AI. It allows users to call LLMs and orchestrate agent calls directly within their Airflow pipelines using decorator-based tasks. The SDK leverages the familiar Airflow @task syntax with extensions like @task.llm, @task.llm_branch, and @task.agent.
Ask HN: Have you written or consumed OpenAPI Arazzo specification?(ycombinator.com) Hi HN,<p>I recently came across the Arazzo specification within the OpenAPI initiative. It defines a standard to express workflows involving multiple APIs. A couple of main use cases here are automatic API invocation with LLMs and automated tests.<p>I want to auto generate API tests based on these specs and would like to see other examples. Is anyone here writing or consuming Arazzo specs?<p>Reference: https://www.openapis.org/arazzo