Open source · Apache Airflow

Making agent runtimes operable.

I contribute provider capabilities to Apache Airflow, with an emphasis on AI agent lifecycle orchestration, cloud operations and the details that make integrations reliable in real DAGs.

10Pull requests authored

8Merged upstream

3Agent clouds covered

Public GitHub snapshot · July 26, 2026

Selected impact

One orchestration layer, three agent clouds.

AWS

Bedrock AgentCore Runtime

Create · Invoke · DeletePR #67984

Google Cloud

Vertex AI Agent Engine

Create · Get · Query · Update · DeletePR #68479

Microsoft Azure

AI Foundry Agents

Create · Update · Run · DeletePR #68799

These integrations let a DAG manage a cloud agent runtime as an explicit lifecycle: provision it, invoke or query it, update it when supported and clean it up. The Agentic Airflow Demo exercises the three paths through the same troubleshooting workflow.

Contribution record

The public trail.

#70160Add Oracle Cloud Infrastructure connection and Generative AI hookOCI · Generative AIOpen #69930Add dedicated Glue crawler lifecycle operatorsAWS GlueMerged #69886Add Amazon ECR repository operatorsAmazon ECRMerged #69386Log SQL query on its own line in BigQueryInsertJobOperatorGoogle BigQueryMerged #68953Fix Breeze SIGILL on Apple Silicon caused by OpenSSL ARM crypto instructionsDeveloper experienceClosed #68799Add Azure AI Foundry Agents operators (Create, Update, Delete, Run)Microsoft Azure · AI agentsMerged #68479Add Vertex AI Agent Engine operators (Create, Get, Query, Update, Delete)Google Cloud · AI agentsMerged #68140Wait for Bedrock AgentCore Runtime deletionAWS · AI agentsMerged #67984Add Amazon Bedrock AgentCore Runtime operatorsAWS · AI agentsMerged #67524Add DmsModifyTaskOperatorAWS DMSMerged