Embabel Agent Framework is a JVM-based framework for building advanced AI agent systems that combine structured programming with large language model interactions to execute complex, goal-oriented workflows. The framework introduces a planning-driven approach where agents dynamically determine sequences of actions required to achieve objectives, rather than relying on fixed pipelines or predefined flows. It models agent behavior through concepts such as goals, actions, and conditions, allowing systems to adapt in real time based on changing inputs and outcomes. Built on top of the Spring ecosystem, it integrates seamlessly with enterprise infrastructure, enabling features like dependency injection, persistence, and transaction management. The framework supports multiple execution modes, including focused, closed, and open systems, each offering different levels of autonomy and flexibility.
Features
- Dynamic planning of agent actions based on goals and conditions
- Integration with JVM and Spring ecosystem for enterprise applications
- Support for multiple execution modes including open and goal-driven systems
- Strongly typed domain models for maintainable agent logic
- Modular architecture enabling reuse and extensibility
- Built-in support for testing and observability of agent workflows