apache/flink-agents

Flink Agents is an Agentic AI framework based on Apache Flink

What it solves

Apache Flink Agents provides a framework for building agentic AI systems. It leverages the stream processing capabilities of Apache Flink to enable the creation of AI agents that can operate on data streams in real-time.

How it works

The framework is built on top of Apache Flink, combining Java and Python components to allow developers to build and deploy agentic AI workflows. It provides a distribution JAR and a Python wheel package for integration.

Who it’s for

Developers and data engineers who are already using Apache Flink or want to build AI agents that require high-throughput, stateful stream processing.

Highlights

  • Agentic AI framework based on Apache Flink
  • Supports both Java and Python
  • Integrated with the Apache Flink ecosystem

Related

  • Project
    scaleapi/scale-agentex

    A framework for building and deploying AI agents that scales from simple chatbots to fully autonomous systems, supporting both synchronous and asynchronous workflows.

  • Project
    agentscope-ai/agentscope

    A production-ready agent framework that provides an SDK and a FastAPI-based service to build, deploy and scale multi-agent applications with built-in RAG and tool management.

  • Project
    i-am-bee/agentstack

    An open infrastructure for turning AI agents into running HTTP services, providing the runtime, LLM routing, and deployment tooling needed to ship agent-powered features.

  • Project
    ag2ai/ag2

    An open-source AgentOS framework for building AI agents and orchestrating their cooperation through a hub-and-channel network system.

  • Project
    AgentEra/Agently

    An AI application runtime framework that provides structured outputs, observable actions, and signal-driven workflows to build reliable, production-ready AI service backends.