The Agent2Agent (A2A) Protocol is an open standard for seamless AI agent communication. It enables agents to discover capabilities, exchange messages, and coordinate workflows across platforms—regardless of their implementation.

Spring AI A2A integrates the A2A Java SDK with Spring AI through Spring Boot autoconfiguration. It seamlessly connects the A2A protocol with Spring AI's ChatClient and tools, enabling you to expose your agents as A2A servers.

This post is part of the Spring AI Agentic Patterns series. While previous posts covered making individual agents more capable (Agent Skills, AskUserQuestionTool, TodoWriteTool, Sub-agent orchestration), this post shows how the A2A Protocol enables agents to…

On behalf of the Spring AI engineering team and everyone who has contributed, we are happy to announce that Spring AI 1.1.0-RC1 has been released and is now available from Maven Central.

This patch release delivers important stability improvements and bug fixes.

Release Summary

This release includes 40 improvements, bug fixes, and documentation updates. The focus of this patch release is on:

• Improvements: 12 enhancements to expand capabilities and functionality
• Stability: 10 bug fixes addressing community-reported issues
• Documentation: 12 improvements to help developers
• Security: 6 dependency upgrades for enhanced security
…

Dear Spring Community,

With the recent announcement of Spring Framework 7.0 and Spring Boot 4.0, the Spring Cloud Data Flow team is pleased to announce the next major release, SCDF 3.0, to align with both Spring Framework 7.0 and Spring Boot 4.0.

This will bring the following SCDF ecosystem of projects in line with Spring Framework 7.0 and Spring Boot 4.0:

• Spring Cloud Data Flow server components (SCDF core and Skipper servers)
• Composed Task Runner, SCDF Shell, Single Step Batch Job, and Task Launcher
• Spring Cloud Deployer Implementations for both Cloud Foundry and Kubernetes
• Spring Cloud Data Flow UI
• Spring Cloud Stream/Task workloads based on Spring Boot 4.0
…

Spring Cloud Data Flow team is pleased to announce the release of 2.7.0 and 2.6.4

While the release 2.6.4 has the bug fixes, the 2.7.0 has the following updates along with the bug fixes and improvements :

SCDF dashboard re-design using VMware Clarity toolkit

SCDF dashboard is re-designed using VMware Clarity design system. This is a complete rewrite of SCDF dashboard GUI to get the benefits of the Clarity design.

Spring Boot 2.3. Update

SCDF server components are now updated to use Spring Boot 2.3.5 release.

Wavefront integration

Spring Cloud Data Flow dashboards for streams, tasks, SCDF server components and Kafka Streams dashboard are available in VMware Wavefront dashboards for integrations. The configurations required to set up the wavefront integration are simplified at the SCDF as well. More information on this can be found here…

Spring Cloud Data Flow team is pleased to announce the release of 2.7.0-M1 and 2.6.3

While the release 2.6.3 has the bug fixes, the first milestone of 2.7.0 has the following enhancements:

SCDF dashboard re-design using VMware Clarity toolkit

SCDF dashboard is re-designed using VMware Clarity design system. This is a complete rewrite of SCDF dashboard GUI to get the benefits of the Clarity design.

Spring Boot 2.3.2 Update

SCDF server components are now updated to use Spring Boot 2.3.2 release.

Wavefront integration

Spring Cloud Data Flow dashboards for streams, tasks and SCDF server components…

Spring Cloud Data Flow team is pleased to announce the first milestone release of 2.6.0.

This 2.6.0-M1 adds some bug fixes and the following features:

• Composed Task Runner as SCDF native module Composed Task Runner is now an integral part of SCDF itself and gets registered implicitly while the users who have the custom composed task runner can still override the native one. This enables us to integrate the composed tasks management within the context of Spring Cloud Data Flow. This change also allowed us to provide some additional user experiences when managing composed tasks. .

• Improvements in task applications management This milestone added some improvements at the backend such as the ability to uniquely identify the task elements inside the composed task, adding task manifest as part of the last ran task definition, ability to cleanup task related resources as part of task definition cleanup along with the SCDF dashboard changes.

  …

Spring Cloud Data Flow team is pleased to announce the first milestone release of 2.5.0.RC1.

This first release candidate of 2.5.0 adds some bug fixes and the following features:

• Support application metadata as part of the Container images. Before this release, we only supported application property whitelisting when using a maven artifact.

• Support for Azure AD integration using OAuth 2.0. Spring Cloud Data Flow, Spring Cloud Skipper servers along with the Spring Cloud Data Flow shell can be configured to integrate with Azure AD for authentication and authorization.

• Removal of Scheduler task launcher component when scheduling tasks. In Spring Cloud Data Flow 2.3.x, the scheduling of tasks was designed to have an intermediate scheduler task launcher component to enhance the continuous deployment user experience. Since this component added some additional complexities and overhead on Kubernetes, the 2.5.x release removed this intermediary task launcher. We also added a migration tool to migrate the schedules from 2.3.x and 2.4.x

  …

Spring Cloud Data Flow team is pleased to announce the first milestone release of 2.5.0.M1.

The first milestone release of 2.5.0 consists of performance improvements addressed at application status retrieval for streams in Cloud Foundry. This also involves revamping the runtime application view page along with better pagination for streams at the SCDF dashboard. You can see more information on these improvements on the recently released SCDF 2.4.2 GA.

This milestone release also consists of some important bug fixes mentioned in here

Please note that Spring Cloud Data Flow 2.5.x is compatible…

Spring Cloud Data Flow team is pleased to announce the GA release of 2.4.2.

In this release, along with some bug fixes, we primarily focused on the server/client-side performance improvements on the stream management.

The REST layer in Spring Cloud Data Flow server is refactored to accommodate better pagination and performance when retrieving the runtime application statuses of streams. In addition to that, the SCDF dashboard pages are re-worked based on these changes. The Runtime Applications page in the Dashboard has a new layout where the runtime applications are grouped by their streams. The Streams page is also refactored to efficiently retrieve the stream status, application…

The Spring Cloud Data Flow team is pleased to announce the milestone release 2.3.0.M1 and the release of 2.2.1 GA.

Along with the bug fixes and enhancements, the first milestone of 2.3.0 also has the following new features:

• Improved Prometheus monitoring based on Prometheus RSocket. It uses persistent bidirectional (RSocket) connections between the Stream/Task applications and a Prometheus RSocket Proxy instance. When Prometheus scrapes the proxy instance, and the proxy, in turn, uses the connections to pull metrics from the applications.
• Ability to pass OAuth Access Token as command-line arguments for Composed Tasks
• Users can now specify a description of the stream when creating it. Thanks to Daniel Serleg for the contribution!
• Spring Cloud Scheduler SPI is now merged into Spring Cloud Deployer. We’ll deprecate the explicit spring-cloud-scheduler project and its implementations on Cloud Foundry, K8s and have them available as part of spring-cloud-deployer…