The Apache Flink Community is excited to announce the release of Apache Flink Agents 0.2.0.
Get access to Flink Agents 0.2.0 now:
Download the release here. Find documentation and quickstart examples here. Note Agents 0.2.0 is a preview version, which means: Some functionalities may contain known or unknown issues. You can check the list of known issues and their resolution status via the Github Issues. The current APIs and configuration options are experimental and may undergo non-backward compatible changes in future versions.

Flink is an open-source stream processing framework for building real-time data applications, offering powerful features for data processing, analytics, and event-driven architectures. Developers can learn about stream processing concepts, event-driven architectures, and real-time analytics techniques to build scalable and fault-tolerant data pipelines for processing large volumes of data in real-time.

Flink

Apache Flink Agents 0.2.0 is now available, bringing event-driven AI agents to Flink's streaming runtime. This preview release adds Java API parity with Python (embedding models, vector stores, MCP server support), expanded ecosystem integrations (Azure OpenAI, Anthropic, Elasticsearch), a redesigned memory system with sensory, short-term, and long-term memory types, and durable execution at code-block granularity. The release supports Flink versions 1.20, 2.0, 2.1, and 2.2, enabling developers to build autonomous agents that process high-volume event streams with millisecond latency and exactly-once consistency.

Apache Flink Agents 0.2.0 Release Announcement