Agent-agnostic evaluation framework with deterministic, command, and LLM judges. Compose judges into juries with configurable voting strategies. Zero coupling to any specific agent implementation.
| Module | Description |
|---|---|
agent-judge-core |
Core Judge API and abstractions (zero external deps) |
agent-judge-exec |
Command execution judges (build, test, coverage) |
agent-judge-llm |
LLM-powered evaluation via Spring AI |
agent-judge-file |
File comparison judges (Java AST, Maven POM, XML, text) |
<dependency>
<groupId>org.springaicommunity</groupId>
<artifactId>agent-judge-core</artifactId>
<version>0.9.1</version>
</dependency>Additional modules:
<artifactId>agent-judge-exec</artifactId>
<artifactId>agent-judge-llm</artifactId>
<artifactId>agent-judge-file</artifactId>// Deterministic judge
Judge buildJudge = BuildSuccessJudge.maven("compile");
// Jury with voting
Jury jury = SimpleJury.builder()
.name("eval")
.judge(buildJudge)
.judge(FileExistsJudge.of("target/classes/App.class"))
.votingStrategy(VotingStrategy.majority())
.build();
Verdict verdict = jury.vote(context);Full API reference, built-in judges, jury system, and voting strategies: https://springaicommunity.mintlify.app/projects/incubating/agent-judge
Apache License 2.0