Embabel, a framework for building AI agents on Java, has reached its 1.0 general-availability release, introducing a planning system borrowed from video game AI to help agents automatically figure out how to accomplish goals. The framework, co-created by Spring Framework founder Rod Johnson, lets Java and Kotlin developers define agents as typed domain objects—goals, actions, and the conditions linking them—rather than manually coding sequences of prompts and tool calls, according to an InfoQ report published this week.
The framework's distinguishing feature is its use of Goal-Oriented Action Planning (GOAP), a technique from video game AI. Instead of following a pre-written script or a fixed graph, the agent receives a set of available actions—each with preconditions and effects—and a planner searches for a sequence that satisfies the goal at runtime. If something changes mid-task (a tool call fails, new information arrives), the planner can reassess and find a new path without the workflow having anticipated that branch in advance. Embabel builds on top of Spring AI, the Spring team's library for calling models, managing embeddings, and invoking tools, rather than replacing it. Because it inherits Spring AI's foundation, Embabel supports most of the providers Spring AI does, including OpenAI, Anthropic, Gemini, Bedrock, Mistral, and DeepSeek, plus local and self-hosted options through Ollama, Docker, or an OpenAI-compatible LMStudio endpoint. Developers can pin an individual action to a specific model, or define role aliases in configuration—a "best" model for steps requiring strong reasoning, a "cheapest" one for routine steps—and have an action reference the role instead of a hard-coded name.
Johnson announced the release with "Embabel 1.0.0 GA nearly ready...excited!" The project's README draws a direct parallel to Spring Framework's history: "An analogy: Spring AI exists at the level of the Servlet API, while Embabel is more like Spring MVC." The report notes that raw servlets work, but every application ends up re-solving the same problems—parsing request parameters, dispatching to the right handler, converting objects to and from HTTP. Spring MVC didn't replace servlets; it sat on top of them and let developers write a typed method signature instead of parsing a HttpServletRequest by hand. Embabel is making the same bet for agents: Spring AI supplies the plumbing to talk to a model, and Embabel supplies the layer where a developer declares "these are my goals and the typed actions available to reach them," leaving the framework to work out the sequencing.
The planning approach sets Embabel apart from LangGraph, the graph-oriented orchestration layer built by LangChain, which Java teams can use directly through LangGraph4j. LangGraph represents an agent workflow as a directed graph where nodes are functions and edges are the routing logic that decides which node executes next, with the developer defining that graph up front. Embabel's planner starts from a different point: rather than the developer wiring the graph, the framework searches for a path through the available typed actions at runtime and can combine actions into sequences the developer never explicitly wired together. The framework supports mixing GOAP planning with explicit state machines in the same agent, so a team can still drop into LangGraph-style fixed routing for the steps where that's what they want. For teams already running Spring Boot services, the report concludes, this release is the point where Embabel stops being a project to watch and starts being one to evaluate.